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

    Neuronpedia

    INDEX
    Explanations

    technical and experimental terms related to scientific research and methods

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

    followed by "using," "with," or "to."

    np_acts-logits-general · gemini-2.0-flash

    using or utilizing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.66
    EndInit
    -0.66
    didSet
    -0.66
    AsStream
    -0.62
     getchar
    -0.61
    \{\\
    -0.60
    الإنجليزية
    -0.58
    Scaler
    -0.56
    орк
    -0.52
    enumi
    -0.51
    POSITIVE LOGITS
     using
    1.59
    using
    1.26
     utilizing
    1.25
     USING
    1.21
     utilisant
    1.21
     Using
    1.20
    Using
    1.20
     with
    1.19
     menggunakan
    1.17
     utilizzando
    1.16
    Act Density 0.935%

    No Known Activations