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

    Neuronpedia

    INDEX
    Explanations

    sentences or clauses where someone is making a statement or giving an opinion.

    oai_token-act-pair · gemini-2.0-flash

    Conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‘
    -3.02
    ’
    -2.92
     “
    -2.91
    ‘
    -2.81
    “
    -2.63
     ’
    -2.47
    ”
    -2.41
    ’”
    -2.33
    …’
    -2.31
    .’
    -2.27
    POSITIVE LOGITS
     يتيمه
    0.59
     ModelExpression
    0.57
    LookAnd
    0.56
     {@
    0.55
     '\\;'
    0.49
     \&
    0.48
     Paglinawan
    0.46
     \#
    0.46
     \%)
    0.46
    RetentionPolicy
    0.46
    Act Density 14.370%

    No Known Activations