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

    Neuronpedia

    INDEX
    Explanations

    the word "high", sometimes also activating on additional words that follow "high"

    oai_token-act-pair · gemini-2.0-flash

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.61
    kloped
    -0.61
    LookAnd
    -0.57
     onOptions
    -0.57
     réus
    -0.56
     ")";
    -0.55
     تضيفلها
    -0.54
    حياتها
    -0.52
     näm
    -0.52
     للاسماء
    -0.51
    POSITIVE LOGITS
     quality
    0.60
    fin
    0.58
    Datuak
    0.55
    gridx
    0.54
    portál
    0.53
    Välislingid
    0.52
     Fin
    0.51
     grain
    0.51
    TabIndex
    0.50
    complexContent
    0.50
    Act Density 0.155%

    No Known Activations