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

    Neuronpedia

    INDEX
    Explanations

    code comments and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     titled
    0.40
    aky
    0.40
    sting
    0.38
    iniz
    0.37
     بعنوان
    0.37
    hof
    0.37
    kker
    0.37
    abut
    0.36
    aline
    0.35
     others
    0.35
    POSITIVE LOGITS
    Created
    1.24
     Created
    1.21
     created
    1.18
    created
    1.09
     creato
    1.08
     créé
    1.05
     creado
    1.02
     creación
    1.02
     созда
    1.00
     creada
    0.97
    Act Density 0.000%

    No Known Activations