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

    Neuronpedia

    INDEX
    Explanations

    various font styles and formatting options

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

    system control and user commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ッシング
    -0.35
    IntoConstraints
    -0.33
     défaite
    -0.32
     picioare
    -0.32
     hlavy
    -0.29
     guste
    -0.29
     muertos
    -0.29
    éndolo
    -0.29
     colgantes
    -0.29
    FileDescriptor
    -0.29
    POSITIVE LOGITS
     propOrder
    0.65
    OGND
    0.59
    cupertino
    0.59
     ModelExpression
    0.57
    stdc
    0.56
     referrerpolicy
    0.55
    VersionUID
    0.52
    bootstrapcdn
    0.51
     հղումներ
    0.51
    èdia
    0.51
    Act Density 0.257%

    No Known Activations