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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    女人
    -0.08
     darling
    -0.07
    forming
    -0.07
    908
    -0.06
    _des
    -0.06
    craper
    -0.06
    bus
    -0.06
    .proj
    -0.06
    Refreshing
    -0.06
    _WH
    -0.06
    POSITIVE LOGITS
     Benton
    0.07
    :::::::::::
    0.06
     Asphalt
    0.06
     lob
    0.06
    <k
    0.06
     mundo
    0.06
     hogy
    0.06
    　ﾊ
    0.06
     grabs
    0.06
    ắn
    0.06
    Act Density 0.000%

    No Known Activations