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

    Neuronpedia

    INDEX
    Explanations

    structure and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rencontres
    0.43
     राख
    0.43
     charms
    0.42
     alcanzar
    0.42
     protéines
    0.42
     allait
    0.41
     सोडा
    0.40
     terzo
    0.40
    чом
    0.39
     meds
    0.39
    POSITIVE LOGITS
     invented
    0.43
    فى
    0.39
    カ
    0.38
     developed
    0.36
    󠁬
    0.36
    Design
    0.36
     unopened
    0.36
    ಂದು
    0.36
     BEGIN
    0.35
    ほどの
    0.35
    Act Density 0.000%

    No Known Activations