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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the singularity or uniqueness of an item or concept

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

    not a single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.59
     INDEP
    -0.51
    OrEqualTo
    -0.47
    Personensuche
    -0.44
    cifix
    -0.39
     independ
    -0.38
    saraba
    -0.38
    tawesome
    -0.38
    ↕
    -0.38
     limitée
    -0.37
    POSITIVE LOGITS
    windowFixed
    0.49
    typeDefinition
    0.48
     EVERY
    0.48
     Every
    0.46
    GIVEREF
    0.45
     every
    0.44
    Every
    0.43
    soever
    0.42
    Chham
    0.41
    Искәрмәләр
    0.41
    Act Density 0.105%

    No Known Activations