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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analogy
    -0.06
    (match
    -0.06
     �
    -0.06
    �
    -0.06
     مشاركة
    -0.06
     объяс
    -0.06
     дослід
    -0.06
    .templates
    -0.06
    ся
    -0.06
    .*
    -0.06
    POSITIVE LOGITS
    toDouble
    0.08
     por
    0.07
    stellen
    0.07
     Writers
    0.06
     Corinth
    0.06
     insurgents
    0.06
     Strawberry
    0.06
     forging
    0.06
    _storage
    0.06
    lettes
    0.06
    Act Density 0.009%

    No Known Activations