Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to machinery and mechanical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after activating tokens

    np_acts-logits-general · gemini-2.0-flash

    shut-off switch, flash lamp, mold, connected windings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haviors
    -0.75
     squishy
    -0.71
     blurry
    -0.70
     tarmac
    -0.69
     velcro
    -0.67
     ponytail
    -0.67
     origami
    -0.66
     sorbet
    -0.66
     muffins
    -0.66
     infinites
    -0.64
    POSITIVE LOGITS
     skall
    0.53
     setempat
    0.51
     inspección
    0.45
     adecuado
    0.45
     adecuados
    0.44
     adecuadas
    0.44
     peralatan
    0.43
     erforder
    0.41
     wyma
    0.41
     required
    0.41
    Act Density 1.664%

    No Known Activations