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

    Neuronpedia

    INDEX
    Explanations

    urls followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রচেষ্টা
    0.31
    lv
    0.30
    asinya
    0.30
    ृता
    0.29
    स्पर
    0.29
    atov
    0.29
    nson
    0.29
    nico
    0.29
    রের
    0.29
    ruption
    0.29
    POSITIVE LOGITS
    이면
    0.31
     udah
    0.29
     Eduard
    0.29
     Eva
    0.29
    󰀄
    0.28
     Feast
    0.28
    Edu
    0.28
     acciaio
    0.28
    Ana
    0.28
    鹃
    0.28
    Act Density 0.002%

    No Known Activations