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

    Neuronpedia

    INDEX
    Explanations

    natural variation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     komen
    0.44
     जमी
    0.43
    unes
    0.42
    Sophie
    0.41
     기본적인
    0.41
    Compiled
    0.40
    compet
    0.39
     egal
    0.39
    razil
    0.38
    Basic
    0.38
    POSITIVE LOGITS
     राख
    0.41
     supernatant
    0.40
     朝
    0.40
    ウエスト
    0.40
     intakes
    0.39
     WR
    0.39
     Supra
    0.39
     Britannica
    0.38
     dark
    0.38
     Mende
    0.38
    Act Density 0.000%

    No Known Activations