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

    Neuronpedia

    INDEX
    Explanations

    log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Count
    -0.07
     blows
    -0.06
     scratching
    -0.06
     Unter
    -0.06
    totalCount
    -0.06
     kulak
    -0.06
     auf
    -0.06
     Special
    -0.06
    _queue
    -0.06
    vekili
    -0.06
    POSITIVE LOGITS
    .ge
    0.07
    ดาห
    0.06
    Protocol
    0.06
    圭圭
    0.06
    .hm
    0.06
     mutually
    0.06
    .clone
    0.06
    产
    0.06
    倫
    0.06
    .GeneratedValue
    0.06
    Act Density 0.006%

    No Known Activations