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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crediting contributions to a work

    oai_token-act-pair · gemini-2.0-flash

    proofreading and editing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.68
     للمعارف
    -0.66
     насељу
    -0.63
    Personendaten
    -0.62
     intptr
    -0.57
    fortawesome
    -0.52
    MigrationBuilder
    -0.52
     ExecuteAsync
    -0.51
    ⓘ
    -0.50
    matchCondition
    -0.50
    POSITIVE LOGITS
     proof
    1.55
     Proof
    1.34
     proofing
    1.30
    proof
    1.28
    Proof
    1.27
     editing
    1.27
     proofs
    1.25
     PROOF
    1.20
     edit
    1.18
     edits
    1.18
    Act Density 1.718%

    No Known Activations