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

    Neuronpedia

    INDEX
    Explanations

    annotations and directives in code

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

    Annotations (e.g., @Override, @SerializedName)

    np_acts-logits-general · gemini-2.0-flash

    class annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.81
     queſta
    -0.79
    oneofs
    -0.77
    Personendaten
    -0.77
     ſelbſt
    -0.71
    ſchaft
    -0.71
    sizeCache
    -0.70
    ſelf
    -0.70
    ſehen
    -0.70
     indígen
    -0.69
    POSITIVE LOGITS
    @
    1.24
     @
    0.83
    #[
    0.68
    //@
    0.53
     *@
    0.52
    ,@
    0.47
    @\
    0.47
    (@
    0.47
    -@
    0.46
    /*@
    0.45
    Act Density 0.030%

    No Known Activations