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

    Neuronpedia

    INDEX
    Explanations

    percentage of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amanho
    0.36
     imminent
    0.35
     للس
    0.35
    ঞ্চল
    0.35
     morgan
    0.34
     alimony
    0.34
    größe
    0.34
     android
    0.34
     vidéo
    0.34
     majeure
    0.33
    POSITIVE LOGITS
     integrada
    0.41
     ника
    0.41
    creva
    0.40
     века
    0.40
     которая
    0.40
     declinations
    0.38
     Declined
    0.38
    eled
    0.37
    鶯
    0.36
     интегри
    0.36
    Act Density 0.001%

    No Known Activations