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

    Neuronpedia

    INDEX
    Explanations

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .values
    -0.06
    еф
    -0.06
    ».
    -0.06
    .).
    -0.06
     情
    -0.06
     "%"
    -0.06
    ylene
    -0.06
     slept
    -0.06
    _legacy
    -0.06
    Hugh
    -0.06
    POSITIVE LOGITS
     geopolitical
    0.07
     BCH
    0.07
    仲
    0.06
    raise
    0.06
    �
    0.06
    岗
    0.06
    _ros
    0.06
     रन
    0.06
    malı
    0.06
     censor
    0.06
    Act Density 0.004%

    No Known Activations