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

    Neuronpedia

    INDEX
    Explanations

    progress not perfection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अर्थात्
    0.46
     assessed
    0.39
     LEGO
    0.38
     liable
    0.36
     substituent
    0.36
     hinsichtlich
    0.35
    வ்வாறு
    0.35
     intravenously
    0.35
    শতঃ
    0.35
     somewhat
    0.34
    POSITIVE LOGITS
    스타그램
    0.55
    photography
    0.53
    _
    0.48
    instagood
    0.47
     yaad
    0.45
     #
    0.44
    Repost
    0.44
    ⌓
    0.43
    forever
    0.43
    ForThe
    0.42
    Act Density 0.220%

    No Known Activations