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

    Neuronpedia

    INDEX
    Explanations

    Loaf pan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abate
    0.94
     cùng
    0.94
     minu
    0.91
     alcan
    0.88
     })_{
    0.84
     incent
    0.83
     diện
    0.81
    ToUpper
    0.79
     modific
    0.78
    ToLower
    0.78
    POSITIVE LOGITS
    و
    0.84
     Motivational
    0.79
    ро
    0.75
    っぱい
    0.74
    ה
    0.74
     बच्चो
    0.73
    ना
    0.71
    कुछ
    0.71
     sicurezza
    0.71
     Якщо
    0.71
    Act Density 0.001%

    No Known Activations