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

    Neuronpedia

    INDEX
    Explanations

    sans-serif fonts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    無
    0.41
     Juan
    0.39
     Fernando
    0.38
    僅
    0.38
    PIN
    0.37
    Disclosure
    0.37
    still
    0.37
    ISR
    0.37
    无
    0.36
     Ini
    0.36
    POSITIVE LOGITS
    achite
    0.46
     pareil
    0.41
     desp
    0.40
    pruch
    0.40
     évalu
    0.39
    doubt
    0.37
     thisTrial
    0.37
     œufs
    0.37
     نفرت
    0.36
     penilaian
    0.36
    Act Density 0.001%

    No Known Activations