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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities of ingredients in recipes

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

    fractions followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataSnapshot
    -0.52
    basicConfig
    -0.50
     pungkasnya
    -0.49
    UnsafeEnabled
    -0.49
     extremos
    -0.46
    Références
    -0.46
     pungkas
    -0.45
    styleType
    -0.45
    EndGlobalSection
    -0.45
    ContentLoaded
    -0.45
    POSITIVE LOGITS
    recy
    0.41
     secret
    0.40
     segre
    0.39
     Perform
    0.37
    VING
    0.36
     secrete
    0.36
    UELA
    0.36
     Wor
    0.36
    unas
    0.35
     pilo
    0.35
    Act Density 0.007%

    No Known Activations