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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competitors
    -0.07
    enso
    -0.07
     dos
    -0.07
    350
    -0.07
     einem
    -0.06
     Imper
    -0.06
     cuc
    -0.06
     veto
    -0.06
     lighten
    -0.06
     Che
    -0.06
    POSITIVE LOGITS
    _ASSERT
    0.07
    .Circle
    0.07
    ./(
    0.06
    	sizeof
    0.06
     виробництва
    0.06
    大全
    0.06
     duy
    0.06
     erót
    0.06
    ισμός
    0.06
    ***/↵
    0.06
    Act Density 0.004%

    No Known Activations