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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Char
    -0.06
    -response
    -0.06
    ForRow
    -0.06
    IFICATIONS
    -0.06
    ,true
    -0.06
     traveling
    -0.06
     scenes
    -0.06
    Mr
    -0.06
    .down
    -0.06
    Window
    -0.06
    POSITIVE LOGITS
    came
    0.07
    ��글
    0.07
    ovky
    0.07
     Tyto
    0.07
     poj
    0.06
    —
    0.06
     mourning
    0.06
     lifestyles
    0.06
    ERVED
    0.06
    ("/{
    0.06
    Act Density 0.012%

    No Known Activations