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

    Neuronpedia

    INDEX
    Explanations

    structured procedural steps or stages in a process

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

    steps and stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     racer
    -0.44
     installer
    -0.44
     Racer
    -0.44
    Racer
    -0.42
     Installer
    -0.41
    接种
    -0.37
    ModelAdmin
    -0.37
    embolso
    -0.37
     trast
    -0.37
     buyer
    -0.36
    POSITIVE LOGITS
    addPreferredGap
    0.56
     preliminary
    0.55
     onPostExecute
    0.53
     etapa
    0.50
     stages
    0.50
    liminary
    0.50
    stages
    0.49
    PreExecute
    0.49
     Initially
    0.49
     этапе
    0.49
    Act Density 0.140%

    No Known Activations