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

    Neuronpedia

    INDEX
    Explanations

    no/any

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Entropy
    -0.07
    .sprites
    -0.06
     alerts
    -0.06
    Jvm
    -0.06
    iction
    -0.06
    .getSelectedItem
    -0.06
    	P
    -0.06
     clan
    -0.06
    _positive
    -0.06
    (tag
    -0.06
    POSITIVE LOGITS
    评价
    0.07
    Did
    0.07
     인
    0.07
    .nd
    0.06
    achte
    0.06
     ними
    0.06
     rendez
    0.06
    """↵↵↵
    0.06
    andise
    0.06
     mai
    0.06
    Act Density 0.054%

    No Known Activations