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

    Neuronpedia

    INDEX
    Explanations

    654

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wall
    -0.08
     Right
    -0.07
    RAW
    -0.07
     safeg
    -0.07
     сет
    -0.07
    .setWindowTitle
    -0.07
     Ting
    -0.07
    oop
    -0.07
     surrounds
    -0.07
    wel
    -0.07
    POSITIVE LOGITS
    657
    0.09
    653
    0.09
    152
    0.09
     Fifty
    0.09
    654
    0.08
    153
    0.08
    157
    0.08
     子
    0.08
    252
    0.08
    650
    0.08
    Act Density 0.146%

    No Known Activations