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

    Neuronpedia

    INDEX
    Explanations

    references to names, identifiers, or elements associated with personal information within data structures

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

    code keywords and function names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bicara
    -0.52
    ecap
    -0.49
    ンダント
    -0.48
    OCCURRED
    -0.47
    askins
    -0.46
     ELEV
    -0.46
    cleros
    -0.46
     sidang
    -0.45
     Ata
    -0.45
     zoude
    -0.44
    POSITIVE LOGITS
    Билгалдахарш
    0.45
    Pozdrawiam
    0.44
     ktorí
    0.43
    Портали
    0.43
     beginnetje
    0.42
    Erreferentziak
    0.42
     autorytatywna
    0.41
     ब्रेकडाउन
    0.41
    Хьажоргаш
    0.41
    RTEE
    0.40
    Act Density 0.105%

    No Known Activations