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

    Neuronpedia

    INDEX
    Explanations

    following lists or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ningún
    0.47
    ות
    0.42
     siempre
    0.41
     nunca
    0.40
    כת
    0.40
    一般的な
    0.40
    sel
    0.39
    Ol
    0.39
    湟
    0.39
     convertirse
    0.38
    POSITIVE LOGITS
     locust
    0.46
    ध्याय
    0.40
     islands
    0.38
     grooves
    0.38
     peacock
    0.38
     consomm
    0.37
     fountains
    0.37
     Rewards
    0.37
    僵
    0.37
    螞
    0.37
    Act Density 0.000%

    No Known Activations