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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or format indicators in the text

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

    words following common introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.72
    aarrggbb
    -0.70
     SDLK
    -0.60
    ">${
    -0.56
    ViewFeatures
    -0.56
    fucking
    -0.55
    setObjectName
    -0.55
    VolleyError
    -0.54
    principalColumn
    -0.53
    ":["
    -0.53
    POSITIVE LOGITS
     recientemente
    0.50
     requerido
    0.50
     éste
    0.50
     contemporáneo
    0.49
     asimismo
    0.49
     subsequently
    0.49
     lisäksi
    0.47
     ésta
    0.47
     pertanto
    0.47
     adecuadamente
    0.45
    Act Density 0.024%

    No Known Activations