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

    Neuronpedia

    INDEX
    Explanations

    Attributions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ificados
    -0.07
    cobra
    -0.07
    _tl
    -0.06
    mium
    -0.06
    thritis
    -0.06
     designated
    -0.06
    iod
    -0.06
    ítica
    -0.06
     lawyers
    -0.06
     census
    -0.06
    POSITIVE LOGITS
    _UNDEF
    0.07
    ]<<
    0.07
    (ofSize
    0.06
    /gui
    0.06
     гри
    0.06
     unn
    0.06
    कन
    0.06
     defaultManager
    0.06
    าะห
    0.06
     llen
    0.06
    Act Density 0.022%

    No Known Activations