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

    Neuronpedia

    INDEX
    Explanations

    listing items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Variante
    0.51
     Exception
    0.48
     Amended
    0.48
     Liability
    0.47
     Đặc
    0.47
     Implementation
    0.47
     Screening
    0.46
    Liability
    0.46
    Послед
    0.45
    $&
    0.44
    POSITIVE LOGITS
     berbagai
    0.74
     sensual
    0.73
     sequins
    0.72
     agradable
    0.72
     allerlei
    0.72
     различных
    0.71
     melodies
    0.70
     imágenes
    0.70
     mindfulness
    0.69
     красо
    0.68
    Act Density 0.001%

    No Known Activations