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

    Neuronpedia

    INDEX
    Explanations

    detailed steps or instructions in a procedural context

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

    numbered steps in a process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PickerController
    -0.48
     DBNull
    -0.46
     DbSet
    -0.46
    richTextPanel
    -0.45
    TagMode
    -0.45
    complexType
    -0.45
     fusca
    -0.44
    esian
    -0.43
    Portale
    -0.42
    mailer
    -0.42
    POSITIVE LOGITS
     step
    0.79
     Steps
    0.79
     steps
    0.77
    Steps
    0.77
     Step
    0.74
    Step
    0.74
    STEP
    0.70
    steps
    0.67
    step
    0.66
     STEPS
    0.66
    Act Density 0.005%

    No Known Activations