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

    Neuronpedia

    INDEX
    Explanations

    steps or instructions related to procedures or processes

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

    Steps or numbered instructions

    np_acts-logits-general · gemini-2.0-flash

    step, then, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.61
     AssemblyTitle
    -0.60
     ddelweddau
    -0.53
    rovna
    -0.51
    RectangleBorder
    -0.50
     Daß
    -0.49
    فوائد
    -0.48
    łaszcza
    -0.48
    cuerdo
    -0.48
    plays
    -0.48
    POSITIVE LOGITS
     step
    0.86
     Then
    0.75
    PositiveButton
    0.75
     Step
    0.71
    Then
    0.71
    enterOuterAlt
    0.70
    Step
    0.70
     then
    0.70
     steps
    0.68
    step
    0.67
    Act Density 0.147%

    No Known Activations