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

    Neuronpedia

    INDEX
    Explanations

    Cyp/Cip prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fair
    -0.07
    kate
    -0.06
    ITY
    -0.06
    �
    -0.06
     воз
    -0.06
    horia
    -0.06
    мотреть
    -0.06
    Increase
    -0.06
     dominated
    -0.06
    ]**
    -0.06
    POSITIVE LOGITS
    _wp
    0.07
    (term
    0.06
     columna
    0.06
     Supplementary
    0.06
    actable
    0.06
     p
    0.06
     гро
    0.06
    兰
    0.06
    ippers
    0.06
    IPP
    0.06
    Act Density 0.016%

    No Known Activations