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

    Neuronpedia

    INDEX
    Explanations

    references to the Hall of Fame and related inductees

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

    Hall of Fame Induction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.54
     autorytatywna
    -0.45
    ➯
    -0.41
    topic
    -0.41
    Nig
    -0.38
    новништво
    -0.38
    response
    -0.37
    pantalones
    -0.37
     Nig
    -0.36
    yves
    -0.36
    POSITIVE LOGITS
     galeria
    0.56
     Museum
    0.49
     Hall
    0.48
    PreInfinity
    0.48
     inducted
    0.48
    endpush
    0.48
     otomatig
    0.47
     galeri
    0.46
     Fame
    0.45
     museum
    0.45
    Act Density 0.024%

    No Known Activations