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

    Neuronpedia

    INDEX
    Explanations

    mandatory and necessary conditions or requirements

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

    must be followed by condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewLabel
    -0.44
    Amicalement
    -0.40
    TextEdit
    -0.38
    ☸
    -0.36
     JButton
    -0.36
     resourceCulture
    -0.35
     incomplète
    -0.35
     hasard
    -0.35
    Fordítás
    -0.34
    @@
    -0.34
    POSITIVE LOGITS
     voldo
    0.54
     sufficiently
    0.51
    蚪
    0.49
     preferably
    0.48
     recognisable
    0.48
     znaj
    0.48
    complexContent
    0.48
     Preferably
    0.47
     balení
    0.47
    ConstraintMaker
    0.46
    Act Density 0.037%

    No Known Activations