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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Distance
    -0.07
    _SAMPL
    -0.07
    .TEXT
    -0.06
    composed
    -0.06
    .r
    -0.06
     credits
    -0.06
    raw
    -0.06
    .Al
    -0.06
     जह
    -0.06
     всем
    -0.06
    POSITIVE LOGITS
    eldon
    0.06
     mockery
    0.06
     breakup
    0.06
     ip
    0.06
     Highlight
    0.06
    (infile
    0.06
     augmentation
    0.06
    ….
    0.06
     Vernon
    0.06
     apiUrl
    0.06
    Act Density 0.000%

    No Known Activations