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

    Neuronpedia

    INDEX
    Explanations

    deduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gravel
    -0.08
     face
    -0.07
    ,test
    -0.07
     GPIO
    -0.07
    _un
    -0.07
     resh
    -0.06
     Clan
    -0.06
     tiles
    -0.06
     phi
    -0.06
    Tracks
    -0.06
    POSITIVE LOGITS
     deductions
    0.13
     deduction
    0.12
     deducted
    0.11
     deduct
    0.09
     deductible
    0.08
    ửi
    0.07
     Dungeons
    0.07
    556
    0.06
     Ded
    0.06
    ators
    0.06
    Act Density 0.001%

    No Known Activations