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

    Neuronpedia

    INDEX
    Explanations

    terms related to encoding processes and their variations

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

    encoding signals and constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iiiiiiii
    -0.47
    AsUp
    -0.44
    RTSC
    -0.43
     ویکی‌پدیا
    -0.42
     DriverManager
    -0.42
    Willi
    -0.42
    лтемелер
    -0.41
    aaaaaaaa
    -0.41
    (!$
    -0.40
    !!!!!!!!!!!!!!!!
    -0.40
    POSITIVE LOGITS
     encode
    1.41
     encoding
    1.36
     encodes
    1.34
     encoded
    1.32
    encoded
    1.28
     Encoding
    1.20
     Encode
    1.18
    Encode
    1.16
    encoding
    1.15
    Encoded
    1.13
    Act Density 0.022%

    No Known Activations