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

    Neuronpedia

    INDEX
    Explanations

    statements or instructions related to identification and matching elements or criteria

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

    appropriateness or correctness

    np_acts-logits-general · gemini-2.0-flash

    questions or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.46
    Географиясе
    -0.36
     مشين
    -0.36
    pintura
    -0.36
    ungkinan
    -0.36
     Bezirk
    -0.36
     Pferde
    -0.36
    maakt
    -0.34
     Orten
    -0.34
     bahkan
    -0.34
    POSITIVE LOGITS
    httphttps
    0.61
     ſind
    0.57
     kasarigan
    0.54
    Rhestr
    0.53
    Diwedd
    0.50
     each
    0.49
    MLLoader
    0.49
    0.49
    CompilerServices
    0.48
    each
    0.47
    Act Density 0.496%

    No Known Activations