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

    Neuronpedia

    INDEX
    Explanations

    capable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Il
    -0.07
    izz
    -0.07
    損
    -0.06
     returns
    -0.06
     Klein
    -0.06
     gardens
    -0.06
    defaults
    -0.06
     UIS
    -0.06
    ρίου
    -0.06
    ούς
    -0.06
    POSITIVE LOGITS
     capable
    0.16
     incapable
    0.09
     phosph
    0.08
    .dirty
    0.07
    hab
    0.07
     capitalist
    0.07
    中华
    0.07
     cata
    0.06
    CRY
    0.06
     способ
    0.06
    Act Density 0.009%

    No Known Activations