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

    Neuronpedia

    INDEX
    Explanations

    ology( produce* most important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کیا
    0.43
     පමණ
    0.42
     は
    0.40
    PatientR
    0.39
     エネルギー
    0.38
     دانش
    0.38
    цією
    0.38
    radeon
    0.38
    調節
    0.37
    sime
    0.37
    POSITIVE LOGITS
     ank
    0.46
     spring
    0.40
    खु
    0.39
    itext
    0.38
    žu
    0.38
     bread
    0.37
    OTP
    0.37
    Bread
    0.37
     Fairness
    0.37
     Recession
    0.36
    Act Density 0.000%

    No Known Activations