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

    Neuronpedia

    INDEX
    Explanations

    statistics and distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invari
    0.43
     fatal
    0.38
    URNIZOR
    0.37
    andfeel
    0.36
     Gaud
    0.35
     metallurgical
    0.35
     لقي
    0.35
    вол
    0.35
     {!
    0.34
    ^{*}$-
    0.34
    POSITIVE LOGITS
     copies
    0.39
     Copies
    0.38
    slit
    0.38
     blacklist
    0.38
    Clear
    0.37
    Phir
    0.37
    慷
    0.36
    frontend
    0.36
     denominations
    0.36
     lists
    0.36
    Act Density 0.001%

    No Known Activations