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

    Neuronpedia

    INDEX
    Explanations

    musical pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mika
    0.40
     misa
    0.39
    祯
    0.38
     мі
    0.37
     posh
    0.37
     Ми
    0.36
     Mic
    0.36
    mgmt
    0.36
     मिरर
    0.35
     미
    0.35
    POSITIVE LOGITS
    Guy
    0.41
     Guy
    0.41
     K
    0.36
    K
    0.35
     d
    0.34
     ダン
    0.33
     G
    0.33
     Dön
    0.32
    G
    0.32
     Adriano
    0.32
    Act Density 0.017%

    No Known Activations