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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating direction or purpose

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

    changes to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.46
    uxxxx
    -0.45
    xymatrix
    -0.44
     فريبيس
    -0.43
    AutoField
    -0.42
     excru
    -0.42
    newtheorem
    -0.40
    zzleHttp
    -0.40
     vectorielle
    -0.40
     BitmapFactory
    -0.39
    POSITIVE LOGITS
     modifications
    0.73
    Modifications
    0.71
     modifying
    0.68
     modifi
    0.67
     modification
    0.67
    modific
    0.67
     Modifications
    0.67
    Modification
    0.66
    modification
    0.65
    modified
    0.65
    Act Density 0.023%

    No Known Activations