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

    Neuronpedia

    INDEX
    Explanations

    mining exploration results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Girl
    -0.07
    ывать
    -0.07
     adlandır
    -0.07
     Girls
    -0.07
     girl
    -0.07
     Wheels
    -0.06
    >Main
    -0.06
     wicht
    -0.06
    .getZ
    -0.06
     doğ
    -0.06
    POSITIVE LOGITS
    astos
    0.06
     persistent
    0.06
    ⟩
    0.06
     Tomáš
    0.06
     التد
    0.06
    agnostic
    0.06
     tit
    0.06
     DS
    0.06
     Croatian
    0.06
     evid
    0.05
    Act Density 0.013%

    No Known Activations