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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Watches
    -0.08
    -icons
    -0.07
    Tx
    -0.07
    _unknown
    -0.07
    Lines
    -0.06
     Markdown
    -0.06
     titan
    -0.06
     watches
    -0.06
    "]]
    -0.06
    GMT
    -0.06
    POSITIVE LOGITS
    becca
    0.08
     bedside
    0.07
     získ
    0.06
    ุร
    0.06
    bring
    0.06
    acterial
    0.06
     humour
    0.06
    śli
    0.06
     ModelAndView
    0.06
    Τ
    0.06
    Act Density 0.002%

    No Known Activations