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

    Neuronpedia

    INDEX
    Explanations

    Formal/Analytical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Came
    -0.07
    ()
    -0.06
     کش
    -0.06
     Sep
    -0.06
    ницы
    -0.06
    �
    -0.06
    ्रस
    -0.06
     utilise
    -0.06
     []
    -0.06
    VIDEO
    -0.06
    POSITIVE LOGITS
     engines
    0.07
     distinguished
    0.07
    icensed
    0.07
    漂
    0.07
    appings
    0.06
     acidic
    0.06
    illas
    0.06
    _reordered
    0.06
    _models
    0.06
    meer
    0.06
    Act Density 0.003%

    No Known Activations