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

    Neuronpedia

    INDEX
    Explanations

    :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ers
    0.46
    -
    0.44
    ies
    0.43
    .
    0.42
    !
    0.41
    jing
    0.34
    ing
    0.34
    ens
    0.34
    net
    0.34
    gment
    0.34
    POSITIVE LOGITS
    ക്കിയ
    0.35
    ानगर
    0.35
    値段
    0.33
    setAutoDraw
    0.32
    कोई
    0.32
     वाढ
    0.30
     компенса
    0.30
    Feels
    0.30
     மொத்தம்
    0.30
    ರುವುದರಿಂದ
    0.30
    Act Density 0.037%

    No Known Activations