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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	rt
    -0.07
     rr
    -0.07
    720
    -0.07
    (rr
    -0.07
    rr
    -0.07
    .walk
    -0.07
     Erotik
    -0.07
    .Task
    -0.07
    inematics
    -0.07
     Orientation
    -0.07
    POSITIVE LOGITS
     Wolfs
    0.08
    Exclude
    0.08
     ولم
    0.08
     وعدم
    0.08
    _except
    0.08
     advantageous
    0.08
     amend
    0.08
     kandidat
    0.08
     domine
    0.08
     dominating
    0.07
    Act Density 0.002%

    No Known Activations