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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or events related to applications, safety, and errors

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

    "Should" or words indicating unexpected situations

    np_acts-logits-general · gemini-2.0-flash

    contingencies and future possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Last
    -0.44
     reaf
    -0.43
     Viel
    -0.41
    load
    -0.40
     makl
    -0.39
     Load
    -0.39
    Distance
    -0.39
    holm
    -0.39
    Load
    -0.38
     load
    -0.38
    POSITIVE LOGITS
    万一
    1.04
     vaikka
    0.89
     accidentally
    0.86
     مرئيه
    0.85
     Normdatei
    0.80
    uxxxx
    0.80
     mocht
    0.79
     вдруг
    0.78
     accidental
    0.78
     someday
    0.76
    Act Density 0.257%

    No Known Activations