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

    Neuronpedia

    INDEX
    Explanations

    fix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bind
    -0.07
    (None
    -0.07
    Profile
    -0.07
    amedi
    -0.07
     Picker
    -0.07
    间
    -0.06
    Collect
    -0.06
    废
    -0.06
    __↵
    -0.06
     skip
    -0.06
    POSITIVE LOGITS
     forts
    0.08
     USPS
    0.07
    ERC
    0.07
    狀態
    0.07
    graphic
    0.07
    saldo
    0.07
    omencl
    0.07
     calam
    0.07
    枲
    0.07
    _real
    0.06
    Act Density 0.045%

    No Known Activations