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

    Neuronpedia

    INDEX
    Explanations

    Callback

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &quot
    -0.08
     bump
    -0.07
     bumps
    -0.07
     kissing
    -0.06
    �
    -0.06
     containment
    -0.06
     phạm
    -0.06
    .Gravity
    -0.06
     GO
    -0.06
     Usa
    -0.06
    POSITIVE LOGITS
    .getName
    0.07
    (MSG
    0.07
    _zero
    0.06
    (Method
    0.06
     PRIV
    0.06
    тот
    0.06
    too
    0.06
     Worker
    0.06
    (TYPE
    0.06
    regex
    0.06
    Act Density 0.000%

    No Known Activations