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

    Neuronpedia

    INDEX
    Explanations

    Needs or desires expressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xunit
    -0.08
     jednou
    -0.07
    stra
    -0.07
    .new
    -0.07
    ست
    -0.06
     والد
    -0.06
    �
    -0.06
     itibar
    -0.06
     Charles
    -0.06
     founders
    -0.06
    POSITIVE LOGITS
    obook
    0.07
    IFORM
    0.06
    etail
    0.06
     bağlantı
    0.06
    apanese
    0.06
     siguiente
    0.06
    鉄道
    0.06
    lify
    0.06
    �
    0.06
    haft
    0.06
    Act Density 0.207%

    No Known Activations