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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or structural patterns in data

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

    Comes before figure or table references

    np_acts-logits-general · gemini-2.0-flash

    shows consideration or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndProject
    -0.62
    featureID
    -0.62
    IsMutable
    -0.57
    новниш
    -0.55
    RUnlock
    -0.54
    DMETHOD
    -0.54
    WriteBarrier
    -0.54
    Derbyniad
    -0.52
    chieht
    -0.52
    MockMvc
    -0.52
    POSITIVE LOGITS
     clearly
    0.39
     Clearly
    0.38
     Note
    0.36
     note
    0.36
     Notice
    0.35
     notes
    0.35
    思
    0.34
     cortes
    0.34
     contrasts
    0.33
    Clearly
    0.32
    Act Density 0.714%

    No Known Activations