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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical values

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

    Numbers inside parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers between 0 and 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mengen
    -0.54
     quatre
    -0.53
     Процитовано
    -0.51
    ACCIÓN
    -0.49
    ɚ
    -0.48
    âneo
    -0.47
    nehm
    -0.47
     privés
    -0.47
    PARTMENT
    -0.47
     impré
    -0.46
    POSITIVE LOGITS
    9
    0.94
    8
    0.88
    4
    0.85
    7
    0.85
    3
    0.85
    6
    0.83
    2
    0.82
    5
    0.81
    1
    0.78
    ьаж
    0.77
    Act Density 1.143%

    No Known Activations