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

    Neuronpedia

    INDEX
    Explanations

    built by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    とも
    0.40
    壕
    0.38
    থের
    0.38
    ালো
    0.37
    Eleven
    0.36
    被告
    0.36
    getAsDouble
    0.35
    éticos
    0.35
    衡量
    0.35
     Helms
    0.34
    POSITIVE LOGITS
     अवै
    0.42
    锶
    0.41
     забруд
    0.40
     जरुरत
    0.39
     조건
    0.38
     pernicious
    0.37
     مخت
    0.37
    уго
    0.36
     blackberry
    0.36
    ᄂ
    0.36
    Act Density 0.000%

    No Known Activations