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

    Neuronpedia

    INDEX
    Explanations

    expressions of celebration or memorable moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    marked by one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.66
    Források
    -0.54
     continúas
    -0.54
     <>",
    -0.53
     autorytatywna
    -0.52
    CodeAttribute
    -0.52
    elemField
    -0.51
    AnchorStyles
    -0.50
     للمعارف
    -0.50
     transférez
    -0.50
    POSITIVE LOGITS
    printStackTrace
    0.40
    Diweddarwch
    0.38
     emperador
    0.35
     elett
    0.34
    過ご
    0.34
    ↩
    0.34
     uLocal
    0.32
     life
    0.32
     mut
    0.30
     subsequence
    0.29
    Act Density 0.108%

    No Known Activations