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

    Neuronpedia

    INDEX
    Explanations

    terms associated with negative impacts or detrimental effects

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

    negative impact or effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁮
    -0.52
    Spoljašnje
    -0.51
    mobileqq
    -0.51
    depuis
    -0.47
    smarty
    -0.46
    foreignKey
    -0.45
    addPreferredGap
    -0.45
     zout
    -0.45
    atown
    -0.44
    AutoSize
    -0.43
    POSITIVE LOGITS
     roadway
    0.69
     roadways
    0.59
     abdomen
    0.51
     grandeur
    0.48
    tieri
    0.48
    ={`${
    0.47
    offsetWidth
    0.47
    stateProvider
    0.46
     cancers
    0.45
     scn
    0.45
    Act Density 0.016%

    No Known Activations