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

    Neuronpedia

    INDEX
    Explanations

    references to settings and preferences

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

    Settings and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manifestazione
    -0.41
    essentiel
    -0.40
     człowie
    -0.40
     erwarten
    -0.38
    insegna
    -0.36
    VersionUID
    -0.32
     geblieben
    -0.32
     vermitteln
    -0.32
    Amérique
    -0.31
     hội
    -0.31
    POSITIVE LOGITS
     utafitiHapana
    0.62
     Settings
    0.60
     onOptions
    0.54
     
    0.52
     settings
    0.51
    OptionsMenu
    0.50
    Settings
    0.49
    openConnection
    0.49
    Билгалдахарш
    0.48
    Quora
    0.47
    Act Density 0.015%

    No Known Activations