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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ">
    -0.07
     тела
    -0.07
     VIII
    -0.07
     عنه
    -0.07
     bırak
    -0.07
    ardım
    -0.07
     hesap
    -0.07
    MEMORY
    -0.07
    -wide
    -0.06
     enviar
    -0.06
    POSITIVE LOGITS
    /trans
    0.06
     minimized
    0.06
    .Tele
    0.06
     Homes
    0.06
    _Anim
    0.06
    .INTEGER
    0.06
    554
    0.05
    (PDO
    0.05
    本
    0.05
     HOME
    0.05
    Act Density 0.006%

    No Known Activations