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

    Neuronpedia

    INDEX
    Explanations

    per month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LAR
    0.91
    на
    0.83
    д
    0.78
    т
    0.77
     ці
    0.76
    та
    0.74
    за
    0.73
    Zeit
    0.73
    다
    0.73
     кіль
    0.73
    POSITIVE LOGITS
     incluido
    1.00
    apeutic
    0.94
     trastornos
    0.94
     bolso
    0.93
     integrado
    0.92
     anuncios
    0.91
     monomials
    0.89
     newest
    0.88
    ubehör
    0.88
    atórios
    0.87
    Act Density 0.000%

    No Known Activations