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

    Neuronpedia

    INDEX
    Explanations

    string comparison ordering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folate
    0.44
    シール
    0.37
     совместно
    0.37
     Others
    0.37
     بیک
    0.37
     bể
    0.37
     Merit
    0.36
     sympat
    0.36
     Regener
    0.36
    ыл
    0.36
    POSITIVE LOGITS
    Ordering
    0.45
    indicate
    0.44
     indicating
    0.43
     indiquant
    0.42
    indicating
    0.41
     indications
    0.40
     indicate
    0.39
     indique
    0.39
     Ordering
    0.39
    返回值
    0.39
    Act Density 0.005%

    No Known Activations