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

    Neuronpedia

    INDEX
    Explanations

    file paths and directories

    oai_token-act-pair · gemini-2.0-flash

    file paths and directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.65
    AccessorTable
    -0.65
    EndContext
    -0.63
    parsedMessage
    -0.59
    ConstraintMaker
    -0.58
    RetentionPolicy
    -0.56
    rxjs
    -0.55
    (&:
    -0.55
    DataAnnotations
    -0.54
    simus
    -0.52
    POSITIVE LOGITS
    ocities
    0.67
    TagMode
    0.56
    :/
    0.54
     cao
    0.54
     menyal
    0.53
    illen
    0.53
     szól
    0.52
     aDecoder
    0.51
    يكب
    0.51
    owned
    0.50
    Act Density 2.010%

    No Known Activations