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

    Neuronpedia

    INDEX
    Explanations

    Code and forum snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وق
    -0.07
     Weaver
    -0.06
     upholstery
    -0.06
    '?
    -0.06
     confidentiality
    -0.06
    :],
    -0.06
     спос
    -0.06
    .INTERNAL
    -0.06
     exhaustion
    -0.06
     ngắn
    -0.06
    POSITIVE LOGITS
    forg
    0.08
    almö
    0.07
    imentary
    0.07
    _GO
    0.06
    isi
    0.06
    elsius
    0.06
    alt
    0.06
    acing
    0.06
    {{
    0.06
    acial
    0.06
    Act Density 0.000%

    No Known Activations