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

    Neuronpedia

    INDEX
    Explanations

    options and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emotionally
    0.42
    enumi
    0.40
    ATION
    0.40
     obtenu
    0.40
     séances
    0.38
     Occupation
    0.37
     Actual
    0.37
     والذي
    0.37
     émotion
    0.37
    knock
    0.37
    POSITIVE LOGITS
     CORS
    0.57
     permitted
    0.46
    getFocusAreas
    0.42
    品質
    0.42
    ૯
    0.41
     لحد
    0.41
    อต
    0.40
     tetrahydro
    0.40
    ែក
    0.40
     Букмекердик
    0.40
    Act Density 0.000%

    No Known Activations