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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :min
    -0.08
     гре
    -0.07
    -footer
    -0.07
    malar
    -0.07
    _vectors
    -0.07
    Screen
    -0.06
    -registration
    -0.06
    呼
    -0.06
    ापस
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Sean
    0.07
    Unix
    0.06
    Closing
    0.06
    Transfer
    0.06
    专业
    0.06
    _AN
    0.06
     eag
    0.06
    lickr
    0.06
    vehicles
    0.05
    RIC
    0.05
    Act Density 0.362%

    No Known Activations