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

    Neuronpedia

    INDEX
    Explanations

    code, URLs, references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.59
     Réponses
    -0.57
    AutoField
    -0.54
     виправивши
    -0.52
     оригіналу
    -0.52
     écoulé
    -0.52
     незавершена
    -0.51
    ModelAdmin
    -0.51
    indt
    -0.50
    FirstResponder
    -0.50
    POSITIVE LOGITS
    sembles
    0.55
     архивлан
    0.53
    談社
    0.51
    lerc
    0.50
    itoneal
    0.48
    seasonal
    0.47
     podí
    0.46
     فريبيس
    0.46
    haka
    0.45
    ineas
    0.45
    Act Density 0.005%

    No Known Activations