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

    Neuronpedia

    INDEX
    Explanations

    biological studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chicks
    -0.07
    (HTTP
    -0.06
    219
    -0.06
    113
    -0.06
    friend
    -0.06
     deflate
    -0.06
    -this
    -0.06
    -about
    -0.06
    ota
    -0.06
     sits
    -0.06
    POSITIVE LOGITS
     введ
    0.07
    madan
    0.07
    การแข
    0.06
     hardcoded
    0.06
    
    0.06
    (reason
    0.06
    พล
    0.06
    ezpeč
    0.06
    ({↵↵
    0.06
    .Generation
    0.06
    Act Density 0.023%

    No Known Activations