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

    Neuronpedia

    INDEX
    Explanations

    comes the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இதில்
    0.31
    ぼ
    0.29
    Sew
    0.29
    Características
    0.28
     fáb
    0.28
    अन्य
    0.28
     uš
    0.28
    CharPtr
    0.28
    叶
    0.28
     সর্ব
    0.27
    POSITIVE LOGITS
     milik
    0.29
     hyperactivity
    0.29
     wreckage
    0.29
    yphenyl
    0.28
     defin
    0.27
     Riviera
    0.27
    apin
    0.27
     sahib
    0.26
     Australia
    0.26
     favored
    0.26
    Act Density 0.000%

    No Known Activations