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

    Neuronpedia

    INDEX
    Explanations

    attributes and parameters related to database actions in code

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

    XML attributes and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.37
     dearly
    -0.34
     shortcut
    -0.34
     mouthful
    -0.34
     mouth
    -0.34
     soeur
    -0.34
     theirs
    -0.33
     birth
    -0.33
     sun
    -0.32
     place
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.86
     HFILL
    0.77
     насељу
    0.74
    دانشنامهٔ
    0.72
     Chwiliwch
    0.70
     Photocase
    0.69
    sidemargin
    0.65
    Хьажоргаш
    0.64
    Personendaten
    0.61
     يتيمه
    0.60
    Act Density 0.008%

    No Known Activations