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

    Neuronpedia

    INDEX
    Explanations

    history buffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ović
    0.46
     Не
    0.46
    Wit
    0.46
    ó
    0.46
     zd
    0.45
     specifica
    0.44
     záp
    0.43
     wit
    0.42
     สูตร
    0.42
     レ
    0.42
    POSITIVE LOGITS
    ة
    0.47
    race
    0.45
     detainees
    0.44
    r
    0.44
    ressive
    0.43
    दृ
    0.42
     زمانہ
    0.42
    病人
    0.42
     Aktion
    0.41
     murderous
    0.41
    Act Density 0.002%

    No Known Activations