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
     Del
    -0.07
    864
    -0.06
    ('
    -0.06
    (Message
    -0.06
     客
    -0.06
    -generation
    -0.06
     dedic
    -0.06
    Generator
    -0.06
     блок
    -0.06
    Nombre
    -0.06
    POSITIVE LOGITS
    lies
    0.07
     nonetheless
    0.06
     thanking
    0.06
     salty
    0.06
     rust
    0.06
    Dispose
    0.06
    &s
    0.06
    _ul
    0.06
     ±
    0.06
    .ToDecimal
    0.06
    Act Density 0.002%

    No Known Activations