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

    Neuronpedia

    INDEX
    Explanations

    gerunds or present participle forms of verbs, often indicating ongoing actions or states

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

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.60
     dignité
    -0.56
     Manajemen
    -0.54
     argint
    -0.53
     termica
    -0.50
    featureID
    -0.49
     demais
    -0.49
     mijne
    -0.48
     Durchmesser
    -0.47
     dignidad
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.66
     needing
    0.51
     being
    0.47
     BEING
    0.44
    자가
    0.44
     having
    0.44
    sizeCache
    0.43
     بيها
    0.43
     getting
    0.42
    数が
    0.42
    Act Density 0.043%

    No Known Activations