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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evrop
    -0.07
    994
    -0.06
     đức
    -0.06
    burger
    -0.06
    ainen
    -0.06
    �
    -0.06
    .ReLU
    -0.06
    .Dispatch
    -0.06
    يمكن
    -0.06
     retarded
    -0.06
    POSITIVE LOGITS
     planet
    0.07
     Utah
    0.07
     Histor
    0.06
     Technology
    0.06
    agnosis
    0.06
    ]--;↵
    0.06
    dictions
    0.06
     varieties
    0.06
    ???
    0.06
    ::_('
    0.06
    Act Density 0.451%

    No Known Activations