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

    Neuronpedia

    INDEX
    Explanations

    Film, modeling, uncomfortable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘧
    0.41
    uh
    0.39
    सवाल
    0.38
     SO
    0.38
    »
    0.38
    К
    0.37
     »
    0.37
    женного
    0.36
    ИТ
    0.35
     Hayashi
    0.35
    POSITIVE LOGITS
     Viewed
    0.38
     Film
    0.38
     कोच
    0.37
     najve
    0.37
     راز
    0.37
     फिल्म
    0.36
    ুদ
    0.36
    ioribus
    0.36
     maxn
    0.36
     film
    0.35
    Act Density 0.000%

    No Known Activations