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

    Neuronpedia

    INDEX
    Explanations

    itar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     společně
    -0.06
     sotto
    -0.06
     faded
    -0.06
     coorden
    -0.06
     kitap
    -0.06
    ._↵
    -0.06
    pecific
    -0.06
     Ca
    -0.06
     ;
↵
↵
    -0.05
    .sex
    -0.05
    POSITIVE LOGITS
    adjust
    0.08
    olist
    0.07
    0.07
    onor
    0.07
     κ
    0.07
     thesis
    0.06
    dataTable
    0.06
     bezpečnost
    0.06
    _deriv
    0.06
    lite
    0.06
    Act Density 0.062%

    No Known Activations