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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and specific directional references

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

    spin direction and plane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     campeones
    -0.40
     متحده
    -0.38
     Walkover
    -0.36
     échou
    -0.36
    Espèce
    -0.35
     pazi
    -0.35
     corretamente
    -0.35
    IBOutlet
    -0.35
    Herkunft
    -0.35
     encuesta
    -0.35
    POSITIVE LOGITS
    setVerticalGroup
    0.65
    xial
    0.59
     orizz
    0.51
     Vertical
    0.50
     horizontal
    0.49
     Horizontal
    0.49
    itudinal
    0.49
     longitudinal
    0.48
     perpendicular
    0.47
     vertical
    0.47
    Act Density 0.237%

    No Known Activations