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

    Neuronpedia

    INDEX
    Explanations

    any size anywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FeatureFlags
    0.65
    ijala
    0.62
    дования
    0.60
    opoietic
    0.60
     և
    0.59
    iosam
    0.58
    nemid
    0.57
    ומי
    0.57
    cuno
    0.56
     beginnetje
    0.56
    POSITIVE LOGITS
     correspondingly
    0.79
     corresponding
    0.65
     outcomes
    0.65
    相应
    0.63
     outcome
    0.63
     myös
    0.63
    房子
    0.63
    कार्यक्रम
    0.62
    结果
    0.61
    对应
    0.61
    Act Density 0.161%

    No Known Activations