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

    Neuronpedia

    INDEX
    Explanations

    organization and breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    N
    0.83
    п
    0.79
    必要な
    0.78
    γγελ
    0.77
     डिस्क्रिप्शन
    0.75
    GEBURTS
    0.75
     nelle
    0.72
    G
    0.71
    NAN
    0.71
    その
    0.69
    POSITIVE LOGITS
    𝓲
    0.82
     THINK
    0.76
     dimers
    0.76
    yati
    0.75
    lerimiz
    0.74
     الشيخ
    0.73
    ילה
    0.72
    ią
    0.71
    𝔂
    0.71
    𝓪
    0.70
    Act Density 0.001%

    No Known Activations