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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alfa
    -0.07
     descendant
    -0.07
    ﰮ
    -0.07
    abbo
    -0.07
    Last
    -0.07
     tutti
    -0.07
    ┖
    -0.07
     Além
    -0.06
    tracer
    -0.06
     odby
    -0.06
    POSITIVE LOGITS
    ONGL
    0.07
    tn
    0.07
    .Link
    0.07
    _DL
    0.06
     sıc
    0.06
     operational
    0.06
     designs
    0.06
     American
    0.06
    -in
    0.06
     weigh
    0.06
    Act Density 0.000%

    No Known Activations