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

    Neuronpedia

    INDEX
    Explanations

    probabilities and estimations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucos
    0.40
     мяс
    0.39
    istence
    0.39
    blo
    0.38
    мино
    0.37
     NEAR
    0.37
     cautious
    0.36
    deel
    0.36
    دة
    0.36
    ドー
    0.36
    POSITIVE LOGITS
    Volume
    0.40
     राज्यात
    0.37
     Audience
    0.37
     Points
    0.36
    Generate
    0.36
    Inflation
    0.36
    Entering
    0.36
     সভায়
    0.36
     Inflammation
    0.36
     جول
    0.35
    Act Density 0.000%

    No Known Activations