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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सारा
    0.60
     mandibular
    0.59
     Beverages
    0.59
     submodule
    0.58
     bodysuit
    0.58
     biotin
    0.57
    是有
    0.57
    elingen
    0.56
     ابراہیم
    0.56
     Volodymyr
    0.55
    POSITIVE LOGITS
     Avent
    0.59
    YES
    0.59
    enos
    0.58
    PUR
    0.57
     широ
    0.57
    矮
    0.55
     velocidade
    0.54
     Clare
    0.53
    Idioma
    0.52
     velocità
    0.52
    Act Density 0.000%

    No Known Activations