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

    Neuronpedia

    INDEX
    Explanations

    assignment and declaration statements in programming contexts

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conocen
    -0.23
     familiar
    -0.22
     hendes
    -0.21
     encuentran
    -0.20
     høy
    -0.20
     længere
    -0.20
     its
    -0.20
     tæn
    -0.19
     مو
    -0.19
    Abp
    -0.19
    POSITIVE LOGITS
     Verſ
    0.96
    ſelben
    0.87
    enderror
    0.86
    [@BOS@]
    0.86
    <unused23>
    0.85
    <unused8>
    0.85
    <unused28>
    0.85
    <unused79>
    0.85
    <unused3>
    0.85
    <unused16>
    0.85
    Act Density 0.431%

    No Known Activations