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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and structures within a text

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

    symbols and numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.77
     فريبيس
    -0.77
    fromnode
    -0.75
    Ӕ
    -0.70
    <unused74>
    -0.65
    <unused41>
    -0.65
    <unused16>
    -0.64
    <unused23>
    -0.64
    <unused14>
    -0.64
    <unused8>
    -0.64
    POSITIVE LOGITS
    conomie
    0.31
    historie
    0.25
     Tourisme
    0.24
     waktu
    0.24
    Symbol
    0.24
     complicada
    0.23
     suyo
    0.23
     asmen
    0.23
    Économie
    0.22
     précédent
    0.22
    Act Density 0.139%

    No Known Activations