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

    Neuronpedia

    INDEX
    Explanations

    TF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Serialized
    -0.07
     존
    -0.07
    統
    -0.07
    層
    -0.06
    _finalize
    -0.06
     đãi
    -0.06
     симптом
    -0.06
    
    -0.06
    .Tools
    -0.06
    Gro
    -0.06
    POSITIVE LOGITS
    (localStorage
    0.08
    вих
    0.07
     ازدواج
    0.07
    леч
    0.07
    .Dense
    0.06
     */
↵
↵
    0.06
    @Override
    0.06
     sigmoid
    0.06
    ................
    0.06
     Clarke
    0.06
    Act Density 1.037%

    No Known Activations