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

    Neuronpedia

    INDEX
    Explanations

    on another, terraform plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рэ
    0.53
    عيد
    0.49
    سة
    0.48
    심
    0.48
    كة
    0.46
    وية
    0.46
     técnicos
    0.45
     shines
    0.44
     GEO
    0.44
    ਰ
    0.43
    POSITIVE LOGITS
     கூறு
    0.49
    mba
    0.46
    ien
    0.45
    ii
    0.45
    ধা
    0.45
    inoza
    0.44
    aña
    0.43
    ique
    0.43
    ila
    0.42
    inz
    0.42
    Act Density 0.000%

    No Known Activations