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

    Neuronpedia

    INDEX
    Explanations

    health concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    沒有
    0.41
     küçük
    0.40
     Ländern
    0.37
    Descriptions
    0.37
    ेशनों
    0.37
    没有
    0.37
    Pairs
    0.36
     Pairs
    0.36
    Cities
    0.36
    Countries
    0.35
    POSITIVE LOGITS
     prowess
    0.51
     shenanigans
    0.48
     mayhem
    0.47
    related
    0.44
     savvy
    0.43
     frenzy
    0.43
     paraphernalia
    0.42
     acumen
    0.42
     related
    0.41
     debacle
    0.41
    Act Density 1.611%

    No Known Activations