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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters used in programming or coding contexts

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

    Code diff output

    np_acts-logits-general · gemini-2.0-flash

    code diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.59
    NewUrlParser
    -0.56
    jsonwebtoken
    -0.54
     HttpStatusCode
    -0.54
    CreateMap
    -0.53
    assigns
    -0.53
    flashdata
    -0.52
    esez
    -0.52
    DriverManager
    -0.51
    FormTagHelper
    -0.49
    POSITIVE LOGITS
     reaſon
    0.76
     purpoſe
    0.75
     myſelf
    0.74
     themſelves
    0.73
     poffible
    0.73
    @@
    0.72
     faſt
    0.72
     Monfieur
    0.71
    ſelves
    0.69
     Anſ
    0.68
    Act Density 0.089%

    No Known Activations