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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    also, too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Xna
    -0.48
    SequentialGroup
    -0.46
    kmale
    -0.46
    ParallelGroup
    -0.45
    lapsingToolbar
    -0.43
     Jacobsen
    -0.42
    Personendaten
    -0.41
    │
    -0.40
    contentLoaded
    -0.40
     Jacobson
    -0.40
    POSITIVE LOGITS
     भी
    0.82
     also
    0.80
    ことも
    0.80
     بھی
    0.71
    人も
    0.71
     cũng
    0.71
     тоже
    0.71
    also
    0.70
    時間も
    0.69
    事も
    0.68
    Act Density 0.006%

    No Known Activations