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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of something or events happening without prior notice

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

    without explanation or prejudice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bort
    -0.47
    queles
    -0.47
     garrafa
    -0.46
     diejenigen
    -0.44
     correctes
    -0.44
    SerializeField
    -0.44
     noiva
    -0.43
     amargo
    -0.43
    <mask>
    -0.43
     sobremesa
    -0.43
    POSITIVE LOGITS
    addGap
    0.52
     Cred
    0.51
     pinulongan
    0.48
     without
    0.48
     الحره
    0.46
    ]),
    0.45
    setStyleSheet
    0.45
     inſ
    0.44
    Coop
    0.44
    claim
    0.44
    Act Density 0.026%

    No Known Activations