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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

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

    names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.44
    Izvori
    -0.32
     Italijani
    -0.31
     milla
    -0.30
     raj
    -0.28
    Referințe
    -0.28
    LabelTagHelper
    -0.27
     onely
    -0.27
    devamını
    -0.27
    PerformLayout
    -0.27
    POSITIVE LOGITS
    armée
    0.56
     nonatomic
    0.54
    SequentialGroup
    0.53
    ⟬
    0.52
     lecciones
    0.51
     AssemblyTitle
    0.51
    horabuena
    0.51
     sizi
    0.50
    agré
    0.49
     Infór
    0.49
    Act Density 0.276%

    No Known Activations