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

    Neuronpedia

    INDEX
    Explanations

    ellipses or omissions in text

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

    code abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.64
    timeScale
    -0.59
    lwjgl
    -0.54
    ConstraintMaker
    -0.53
    ValueStyle
    -0.52
    IntoConstraints
    -0.52
    __":
    -0.51
    StackNavigator
    -0.51
    UserScript
    -0.51
    SequentialGroup
    -0.49
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.48
    hoeddwyd
    0.43
     affari
    0.40
     stuff
    0.40
     Somewhere
    0.40
     HasFactory
    0.39
    pośred
    0.39
     etc
    0.38
     vertrou
    0.37
     razonable
    0.37
    Act Density 0.042%

    No Known Activations