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

    Neuronpedia

    INDEX
    Explanations

    terms related to errors and performance degradation in systems

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

    avoiding undesirable conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.43
    lander
    -0.37
     entr
    -0.36
     Spi
    -0.36
     البر
    -0.35
    orado
    -0.35
     colo
    -0.35
    doing
    -0.35
     SAF
    -0.35
    Came
    -0.34
    POSITIVE LOGITS
     preocu
    0.49
    :✨
    0.48
    存于互联网档案馆
    0.47
     muchacha
    0.47
     Gefühl
    0.46
     ragazze
    0.45
     Forderung
    0.44
    AllowUser
    0.44
     inneces
    0.43
    jercicio
    0.43
    Act Density 0.059%

    No Known Activations