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

    Neuronpedia

    INDEX
    Explanations

    Ste

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pu
    0.93
    wat
    0.83
    forme
    0.82
    jani
    0.79
    bagian
    0.78
    culis
    0.78
    愀
    0.77
    pent
    0.76
    batas
    0.76
    ching
    0.76
    POSITIVE LOGITS
    TY
    0.87
     о
    0.76
    RI
    0.76
    NOS
    0.74
     т
    0.73
    íe
    0.71
     রেলস্ট
    0.70
    erys
    0.70
     RIA
    0.69
    емо
    0.68
    Act Density 0.000%

    No Known Activations