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

    Neuronpedia

    INDEX
    Explanations

    when X happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dört
    0.48
    dört
    0.48
     juries
    0.46
    treat
    0.45
    cPix
    0.45
    पूर्ति
    0.45
     vecin
    0.45
    ໃຈ
    0.45
    ရေး
    0.44
     большей
    0.44
    POSITIVE LOGITS
    H
    0.46
    pronounced
    0.44
    Mac
    0.43
    SB
    0.43
    B
    0.42
     Overview
    0.41
     awal
    0.41
    LH
    0.40
    AL
    0.39
     absch
    0.39
    Act Density 0.000%

    No Known Activations