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

    Neuronpedia

    INDEX
    Explanations

    str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -packed
    -0.07
     đến
    -0.07
    сет
    -0.07
    chez
    -0.07
     UInt
    -0.07
     nós
    -0.07
    当
    -0.07
     ★
    -0.06
    celona
    -0.06
    ;++
    -0.06
    POSITIVE LOGITS
    花钱
    0.07
     entering
    0.07
    _aw
    0.06
    district
    0.06
     injection
    0.06
    ארגון
    0.06
    釜
    0.06
     baseman
    0.06
     script
    0.06
     recru
    0.06
    Act Density 0.001%

    No Known Activations