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

    Neuronpedia

    INDEX
    Explanations

    elements related to verification and confirmation processes

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

    Czech/Slovak/Croatian language fragments

    np_acts-logits-general · gemini-2.0-flash

    potvrda prijave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +:+
    -0.68
    tagHelperRunner
    -0.68
     snippetHide
    -0.65
     AspNetCore
    -0.64
    ADATA
    -0.62
     GenerationType
    -0.61
    ftagPool
    -0.60
    tahankan
    -0.58
    原始内容存档于
    -0.58
     }{@
    -0.57
    POSITIVE LOGITS
    ification
    0.46
    πισ
    0.44
    _{-\
    0.43
    الحياه
    0.42
    ilove
    0.42
    dificio
    0.42
    imento
    0.42
    <bos>
    0.41
     visual
    0.41
     Kais
    0.41
    Act Density 0.056%

    No Known Activations