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

    Neuronpedia

    INDEX
    Explanations

    credit score, DTC, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल्डर
    0.40
    रियल
    0.39
     Contribution
    0.39
    ס
    0.39
     ہر
    0.38
    த்தி
    0.38
     contributory
    0.38
    சர
    0.38
     الوا
    0.38
     immunost
    0.38
    POSITIVE LOGITS
    azo
    0.41
    ụ
    0.40
    fecha
    0.40
    ahlen
    0.40
    ó
    0.40
    Primera
    0.39
    RootNamespace
    0.39
     fuerte
    0.38
    ivet
    0.38
    ults
    0.38
    Act Density 0.001%

    No Known Activations