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

    Neuronpedia

    INDEX
    Explanations

    expressions related to transitions and changes in status or roles

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

    Reverting to a previous state

    np_acts-logits-general · gemini-2.0-flash

    returning or restoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.41
    insatz
    -0.41
     sema
    -0.38
     potential
    -0.37
    SaveChangesAsync
    -0.36
    blurRadius
    -0.36
     optional
    -0.36
    tonode
    -0.35
     understanding
    -0.35
     exchange
    -0.35
    POSITIVE LOGITS
     kembali
    0.65
     wieder
    0.60
     tilbage
    0.59
     обратно
    0.59
    WebVitals
    0.57
    mbalikan
    0.57
     restored
    0.57
     tillbaka
    0.55
     novamente
    0.54
     tilbake
    0.54
    Act Density 0.649%

    No Known Activations