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

    Neuronpedia

    INDEX
    Explanations

    Old Man and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nan
    0.44
     Nan
    0.42
    ديث
    0.41
     Bryn
    0.40
    녠
    0.40
    ITECT
    0.39
    윰
    0.39
     Beth
    0.39
    Stu
    0.38
    筋
    0.38
    POSITIVE LOGITS
     Johnny
    0.54
     Eddie
    0.52
     Leroy
    0.51
    Eddie
    0.50
     Levi
    0.48
    Johnny
    0.46
     Gabriel
    0.46
     Julius
    0.45
     Lula
    0.45
     Felix
    0.45
    Act Density 0.001%

    No Known Activations