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

    Neuronpedia

    INDEX
    Explanations

    XML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FF
    -0.07
     alcohol
    -0.06
    archive
    -0.06
    _variable
    -0.06
    BIT
    -0.06
     Chamber
    -0.06
    sahuje
    -0.06
     TextArea
    -0.06
    Forest
    -0.06
    비
    -0.06
    POSITIVE LOGITS
    τωση
    0.08
    ...");↵↵
    0.07
    уються
    0.07
    raphic
    0.07
     unlaw
    0.06
    _bins
    0.06
     αυ
    0.06
    sehen
    0.06
    ?action
    0.06
     khả
    0.06
    Act Density 0.009%

    No Known Activations