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

    Neuronpedia

    INDEX
    Explanations

    looks around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étudiant
    1.03
     Königreich
    1.02
     ekonomi
    1.02
     responsabilità
    1.02
    लैंड
    1.01
     américaine
    1.01
     iż
    0.98
     améric
    0.96
    体の
    0.96
    その他の
    0.96
    POSITIVE LOGITS
    or
    1.11
    וני
    0.89
    asci
    0.86
    فات
    0.79
    Abs
    0.79
    शब्द
    0.79
    ar
    0.77
     Dieser
    0.76
     tinker
    0.76
    这对
    0.76
    Act Density 0.001%

    No Known Activations