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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >:</
    -0.06
    .visitVarInsn
    -0.06
     miscon
    -0.06
    写
    -0.06
    mesini
    -0.06
    .Mouse
    -0.06
    ナー
    -0.06
    사람
    -0.06
    ikes
    -0.06
    eltas
    -0.06
    POSITIVE LOGITS
    ۱۰
    0.07
    unded
    0.07
     +↵
    0.07
     λο
    0.06
     Retry
    0.06
    ars
    0.06
     пять
    0.06
    10
    0.06
    _nick
    0.06
    .De
    0.06
    Act Density 0.001%

    No Known Activations