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

    Neuronpedia

    INDEX
    Explanations

    indicators of successful actions or events

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

    user confirmation messages, status updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.62
     &___
    -0.61
     protoimpl
    -0.60
    OGND
    -0.52
    quelize
    -0.48
    istoitu
    -0.47
    SpringRunner
    -0.46
    AxisAlignment
    -0.46
     CreateTagHelper
    -0.45
    RTLD
    -0.45
    POSITIVE LOGITS
    abestanden
    0.52
    flashdata
    0.49
     kasarigan
    0.47
    Successfully
    0.35
     Mention
    0.35
     faptul
    0.34
    Przypisy
    0.33
    Toast
    0.33
     протя
    0.33
     poule
    0.33
    Act Density 0.004%

    No Known Activations