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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rong
    -0.07
    .ignore
    -0.07
    program
    -0.07
    女主
    -0.06
     AppModule
    -0.06
    .mouse
    -0.06
    .Arg
    -0.06
     לב
    -0.06
    ἀ
    -0.06
    _abs
    -0.06
    POSITIVE LOGITS
    oseconds
    0.07
    (tile
    0.07
    就得
    0.07
    _Error
    0.06
    随时
    0.06
    冰淇淋
    0.06
    Socket
    0.06
     -->↵↵
    0.06
    ghan
    0.06
    쉐
    0.06
    Act Density 0.012%

    No Known Activations