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

    Neuronpedia

    INDEX
    Explanations

    terms related to file and access permissions

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

    German words and phrases

    np_acts-logits-general · gemini-2.0-flash

    Verzeichnis-Listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.51
     on
    -0.49
     by
    -0.47
     to
    -0.47
     of
    -0.47
     vare
    -0.47
     with
    -0.46
    ers
    -0.46
     for
    -0.44
    s
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    1.00
     Shakspeare
    0.90
     Anſ
    0.88
     Majefty
    0.88
     pleaſure
    0.85
     Shaksp
    0.84
     myſelf
    0.81
    Obrázky
    0.81
     itſelf
    0.81
     leaſt
    0.81
    Act Density 0.046%

    No Known Activations