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

    Neuronpedia

    INDEX
    Explanations

    gaining strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াইন
    0.41
    axel
    0.41
    complexity
    0.39
     century
    0.38
    details
    0.38
    invasion
    0.37
    century
    0.37
    返回值
    0.36
    ouille
    0.36
     consequential
    0.36
    POSITIVE LOGITS
    ండు
    0.43
     drawing
    0.42
    ᒫ
    0.39
    ニック
    0.39
    راءة
    0.38
    筋
    0.37
     {'
    0.36
     harus
    0.36
    undu
    0.35
    銥
    0.35
    Act Density 0.000%

    No Known Activations