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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Esc
    -0.07
    alt
    -0.07
     болез
    -0.07
    (components
    -0.06
    _visual
    -0.06
     AD
    -0.06
    rote
    -0.06
    Presentation
    -0.06
    Gray
    -0.06
    (shell
    -0.06
    POSITIVE LOGITS
     crim
    0.08
    oyo
    0.07
    itial
    0.06
    -catching
    0.06
     lstm
    0.06
    endimento
    0.06
    <Comment
    0.06
     Rein
    0.06
    ("~/
    0.06
    níky
    0.06
    Act Density 0.013%

    No Known Activations