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

    Neuronpedia

    INDEX
    Explanations

    confines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motion
    -0.08
    电磁
    -0.07
     gray
    -0.07
    糊涂
    -0.07
     assh
    -0.07
     ordered
    -0.07
    apor
    -0.07
    咿
    -0.07
     Melania
    -0.07
    ricular
    -0.07
    POSITIVE LOGITS
     Graves
    0.07
    estination
    0.07
    .server
    0.07
     reinc
    0.07
    ']);
    0.07
    🌋
    0.07
    comboBox
    0.06
    휠
    0.06
     relent
    0.06
    :X
    0.06
    Act Density 0.001%

    No Known Activations