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

    Neuronpedia

    INDEX
    Explanations

    social events/life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Explicit
    -0.07
     proclaimed
    -0.07
     Bene
    -0.06
    .clientHeight
    -0.06
    静
    -0.06
    .tt
    -0.06
    ement
    -0.06
    .Properties
    -0.06
    цин
    -0.06
     Superman
    -0.06
    POSITIVE LOGITS
    bob
    0.07
    애
    0.06
    _CHOICES
    0.06
    /proto
    0.06
     HAPP
    0.06
    _Interface
    0.06
    _PICTURE
    0.06
    Australia
    0.06
     differing
    0.06
    imore
    0.06
    Act Density 0.176%

    No Known Activations