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

    Neuronpedia

    INDEX
    Explanations

    functions related to string manipulation

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

    string trimming operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.94
    findpost
    -0.89
     صوتيه
    -0.79
     мәкал
    -0.79
     виправивши
    -0.75
    ⓧ
    -0.75
    évaluateur
    -0.74
     informée
    -0.73
     autorytatywna
    -0.73
     InputDecoration
    -0.72
    POSITIVE LOGITS
     Pacífico
    0.37
    rstrip
    0.34
     térmico
    0.34
    良く
    0.32
    よく
    0.30
     jurisdic
    0.28
     sinistro
    0.27
     aérea
    0.27
     Satz
    0.27
    strip
    0.26
    Act Density 0.002%

    No Known Activations