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

    Neuronpedia

    INDEX
    Explanations

    presentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .h
    -0.06
    (progress
    -0.06
    .uri
    -0.06
    /content
    -0.06
     cloth
    -0.06
     compressed
    -0.06
     disob
    -0.06
     regex
    -0.06
     legitimacy
    -0.06
    [line
    -0.06
    POSITIVE LOGITS
    Presentation
    0.07
     Parade
    0.07
    unexpected
    0.07
     presume
    0.06
     sep
    0.06
     mains
    0.06
    ｭ
    0.06
     Outline
    0.06
     이렇게
    0.06
     yanıt
    0.06
    Act Density 0.006%

    No Known Activations