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

    Neuronpedia

    INDEX
    Explanations

    quoted strings or text between quotation marks

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

    command line flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setMsg
    -0.47
    chestra
    -0.47
     שוליים
    -0.45
     mắn
    -0.45
    jecture
    -0.45
     Audits
    -0.44
     Maio
    -0.44
     Volley
    -0.44
     Audit
    -0.43
     Barkley
    -0.42
    POSITIVE LOGITS
    ("-
    1.63
    ('-
    1.49
     "-
    1.48
     '-
    1.40
    ="-
    1.32
     [-
    1.05
    :"-
    1.01
    '-
    0.99
    ("-",
    0.96
    }{-
    0.92
    Act Density 0.033%

    No Known Activations