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

    Neuronpedia

    INDEX
    Explanations

    programming code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anticipation
    0.43
     franchises
    0.34
     pursuit
    0.34
     casework
    0.34
     franchise
    0.34
    許可
    0.33
    幼稚
    0.33
    라면
    0.33
     replication
    0.32
    访
    0.32
    POSITIVE LOGITS
    amsmath
    0.49
     चिंत
    0.41
    aklar
    0.40
    mathbb
    0.40
    mány
    0.40
    ÃO
    0.39
    인트
    0.39
    Url
    0.39
    ざ
    0.38
     योग
    0.37
    Act Density 0.000%

    No Known Activations