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

    Neuronpedia

    INDEX
    Explanations

    numeric values or sequences

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

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.80
     kasarigan
    -0.78
    scriptcase
    -0.73
    verifyException
    -0.73
    цездатний
    -0.72
    oa̍t
    -0.71
    msgTypes
    -0.69
    GEBURTSDATUM
    -0.69
    Vidite
    -0.69
    ніципа
    -0.69
    POSITIVE LOGITS
    ’
    0.41
     rayas
    0.39
     desperdic
    0.39
     petición
    0.38
     again
    0.38
    ándolo
    0.38
     Travail
    0.36
     puntuación
    0.36
     mejora
    0.36
     saída
    0.36
    Act Density 0.130%

    No Known Activations