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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRTUAL
    -0.07
    .fold
    -0.07
     Speaking
    -0.07
    _neurons
    -0.06
    sessionId
    -0.06
    内部
    -0.06
     sewage
    -0.06
    _VIDEO
    -0.06
     dual
    -0.06
    HANDLE
    -0.06
    POSITIVE LOGITS
     nosso
    0.07
    quarters
    0.06
    े,
    0.06
    ейств
    0.06
    umer
    0.06
    wyn
    0.06
     specializing
    0.06
     ،
    0.06
     польз
    0.06
     今
    0.06
    Act Density 0.000%

    No Known Activations