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

    Neuronpedia

    INDEX
    Explanations

    gendered pronouns and "if".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.70
    BagConstraints
    -0.70
    IBOutlet
    -0.65
    OrNil
    -0.63
    setVerticalGroup
    -0.61
     initComponents
    -0.56
    PerformLayout
    -0.55
    elemField
    -0.54
    AutoresizingMask
    -0.54
    dAtA
    -0.53
    POSITIVE LOGITS
     been
    0.77
     be
    0.69
    htë
    0.67
    ).__
    0.65
     always
    0.56
     lehe
    0.56
    ">//
    0.55
     definitely
    0.54
     essere
    0.54
     also
    0.54
    Act Density 0.127%

    No Known Activations