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

    Neuronpedia

    INDEX
    Explanations

    instances of speech and dialogue attribution

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

    Attribution or quotations

    np_acts-logits-general · gemini-2.0-flash

    reporting speech or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.56
    
    -0.48
    :✨
    -0.47
     ?>/
    -0.44
    __':
    -0.44
    rungsseite
    -0.43
     تانيه
    -0.42
     canst
    -0.42
    WithMany
    -0.42
    __).
    -0.42
    POSITIVE LOGITS
     Савезне
    0.62
    GOTREF
    0.52
     للاسماء
    0.50
    AccessorTable
    0.44
     TAMBÉM
    0.44
    protetor
    0.43
    impianto
    0.42
     Saludos
    0.42
    LookAnd
    0.40
     Semoga
    0.39
    Act Density 0.227%

    No Known Activations