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

    Neuronpedia

    INDEX
    Explanations

    questions related to math or definitions

    oai_token-act-pair · gemini-2.0-flash

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.80
    ">//
    -0.63
    iatric
    -0.61
    хьтан
    -0.58
    انيف
    -0.57
     hvad
    -0.57
    structors
    -0.55
     Roskov
    -0.55
    extAlignment
    -0.55
    पया
    -0.54
    POSITIVE LOGITS
    PerformLayout
    0.64
     sớm
    0.50
     undersigned
    0.50
     <>",
    0.49
    Altri
    0.48
    oub
    0.47
    addView
    0.47
    ateri
    0.47
     Sleeps
    0.47
     opgenomen
    0.45
    Act Density 1.374%

    No Known Activations