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

    Neuronpedia

    INDEX
    Explanations

    Making arguments or assertions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posium
    -0.07
    _motion
    -0.06
    _cond
    -0.06
    ьют
    -0.06
     Join
    -0.06
     uf
    -0.06
     getList
    -0.06
     noticed
    -0.06
     Yan
    -0.06
    (seconds
    -0.06
    POSITIVE LOGITS
    gün
    0.06
    HWND
    0.06
     závod
    0.06
     ห
    0.06
    Ř
    0.06
    」「
    0.06
    irket
    0.05
     nosotros
    0.05
     Giov
    0.05
    ธน
    0.05
    Act Density 0.310%

    No Known Activations