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

    Neuronpedia

    INDEX
    Explanations

    lexicon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     televiz
    -0.09
     sometime
    -0.08
     princípio
    -0.08
    інде
    -0.08
    Sous
    -0.08
    ECD
    -0.08
     предложение
    -0.08
     شاشة
    -0.07
     :::::
    -0.07
     painter
    -0.07
    POSITIVE LOGITS
     predefined
    0.11
     predetermined
    0.09
    Triggers
    0.09
    known
    0.09
     indicative
    0.09
     triggers
    0.08
     positives
    0.08
     known
    0.08
     известных
    0.08
    woorden
    0.08
    Act Density 0.004%

    No Known Activations