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

    Neuronpedia

    INDEX
    Explanations

    expressions of negation or absence of something

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

    "no" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    no followed by qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comigo
    -0.61
     متعلقه
    -0.60
     suivantes
    -0.60
    seamnă
    -0.59
     laquelle
    -0.59
     evolucion
    -0.57
     což
    -0.56
     tradicionais
    -0.55
     vendus
    -0.55
     isso
    -0.55
    POSITIVE LOGITS
     real
    0.81
     no
    0.76
     more
    0.73
     particular
    0.71
     further
    0.69
     idea
    0.69
    memcmp
    0.68
     other
    0.67
     evidence
    0.66
     chance
    0.66
    Act Density 0.218%

    No Known Activations