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

    Neuronpedia

    INDEX
    Explanations

    ownership and reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.84
    的には
    0.75
    금
    0.73
     정신
    0.73
    하신
    0.71
    하
    0.70
    د
    0.69
    髪
    0.69
    Жи
    0.68
     시행
    0.68
    POSITIVE LOGITS
    zingen
    0.76
     hongos
    0.73
    ξε
    0.72
     Interesting
    0.71
    ickou
    0.70
    mette
    0.69
     należy
    0.69
    chodzi
    0.68
    iapan
    0.68
     episodios
    0.68
    Act Density 0.000%

    No Known Activations