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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional or hypothetical language related to actions and processes

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

    cases involving non-citizens or models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lösungs
    -0.36
     Privacidad
    -0.36
     suivante
    -0.34
     Flüssigkeit
    -0.33
    MVH
    -0.33
     fiume
    -0.32
    حياته
    -0.32
     alors
    -0.32
    oltre
    -0.31
     timeType
    -0.31
    POSITIVE LOGITS
     createContext
    0.61
     CreateTagHelper
    0.55
    Revenir
    0.51
     الحره
    0.49
     فريبيس
    0.49
     ExecuteAsync
    0.48
    addCriterion
    0.48
    setViewportView
    0.48
    DrawerToggle
    0.47
     AssemblyTitle
    0.46
    Act Density 0.053%

    No Known Activations