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
     distinguished
    -0.07
    bv
    -0.06
    ppe
    -0.06
    рити
    -0.06
    αιο
    -0.06
    Signal
    -0.06
    批
    -0.06
    폰
    -0.06
    iterations
    -0.06
     Million
    -0.06
    POSITIVE LOGITS
     Bind
    0.06
    ,['
    0.06
    0.06
    @click
    0.06
     мире
    0.06
     swingers
    0.06
    цією
    0.06
    .constructor
    0.06
    습
    0.06
     dynamic
    0.06
    Act Density 0.031%

    No Known Activations