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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to mathematical operations or expressions

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

    division calculation involving 126

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Llo
    -0.41
     RouterModule
    -0.41
     Poh
    -0.41
    Rö
    -0.36
     Talley
    -0.35
     Arora
    -0.35
     Rö
    -0.35
     brings
    -0.35
     Prit
    -0.34
     take
    -0.34
    POSITIVE LOGITS
    tagHelperRunner
    0.69
    IntoConstraints
    0.66
    ktop
    0.64
    GEBURTSDATUM
    0.64
    новниш
    0.62
    Personendaten
    0.61
    URBANA
    0.60
     الحره
    0.60
     المعرف
    0.59
    principalColumn
    0.58
    Act Density 0.048%

    No Known Activations