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

    Neuronpedia

    INDEX
    Explanations

    terms related to bug tracking and status updates

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

    test case states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.42
     hinaus
    -0.40
     vooraf
    -0.39
     godz
    -0.39
     masing
    -0.38
     alluded
    -0.36
    wijl
    -0.35
     Hin
    -0.35
     upside
    -0.34
     antemano
    -0.34
    POSITIVE LOGITS
    WriteTagHelper
    0.57
     '\\;'
    0.54
     Administrativna
    0.50
    MigrationBuilder
    0.49
    ✭✭
    0.48
    astify
    0.45
     CreateTagHelper
    0.45
     vPvB
    0.45
    Controllo
    0.45
    osoba
    0.44
    Act Density 0.251%

    No Known Activations