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

    Neuronpedia

    INDEX
    Explanations

    references to anonymous reviewers and their feedback in the context of peer review

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

    review or referee comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.53
    }{*}{}
    -0.50
    oa̍t
    -0.48
    AddressBook
    -0.47
    TabIndex
    -0.46
    Filmographie
    -0.46
    GeneratedMessage
    -0.45
    :+:
    -0.45
    Enti
    -0.45
    Parcelize
    -0.44
    POSITIVE LOGITS
     reviewers
    0.60
     peer
    0.59
     anonymous
    0.59
     expert
    0.58
     reviewer
    0.53
    expert
    0.51
     referees
    0.51
     Reviewer
    0.49
    Reviewer
    0.49
     anonymously
    0.49
    Act Density 0.041%

    No Known Activations