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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performed actions or operations

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

    "on" followed by determiners or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الاطلاع
    -0.42
     būti
    -0.32
     kjent
    -0.30
    getenv
    -0.29
    querySelector
    -0.28
     waiting
    -0.28
    hæng
    -0.28
    getMenuInflater
    -0.28
     comprom
    -0.27
     ég
    -0.27
    POSITIVE LOGITS
    IVEREF
    0.64
    WebVitals
    0.64
    нгред
    0.62
    ImageContext
    0.61
    ſſung
    0.61
    対象
    0.60
     noDo
    0.60
    𓇠
    0.60
    ੝
    0.60
    ſicht
    0.59
    Act Density 0.213%

    No Known Activations