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

    Neuronpedia

    INDEX
    Explanations

    Tokens starting with underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gameObject
    -0.08
    	st
    -0.07
    .offer
    -0.06
     exciting
    -0.06
    .diag
    -0.06
    	out
    -0.06
    -validation
    -0.06
     звіль
    -0.06
    Inspect
    -0.06
     digitalWrite
    -0.06
    POSITIVE LOGITS
     Chapter
    0.07
     engines
    0.07
     çok
    0.06
     NAMES
    0.06
     Sporting
    0.06
     davran
    0.06
    Highest
    0.06
    GN
    0.06
     harassment
    0.06
    ��
    0.06
    Act Density 0.003%

    No Known Activations