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

    Neuronpedia

    INDEX
    Explanations

    Code and technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شهر
    -0.06
     almacen
    -0.06
     Spotify
    -0.06
    еть
    -0.06
    PIO
    -0.06
    Embed
    -0.06
     race
    -0.06
     posición
    -0.06
     컨
    -0.06
     Finish
    -0.06
    POSITIVE LOGITS
     prive
    0.07
    fieldName
    0.07
     Hind
    0.06
    sk
    0.06
    .priv
    0.06
     london
    0.06
     ва
    0.06
     archivo
    0.06
     cherche
    0.06
    ्रभ
    0.06
    Act Density 0.000%

    No Known Activations