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

    Neuronpedia

    INDEX
    Explanations

    -NLS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ový
    -0.07
     jury
    -0.06
     proofs
    -0.06
     prog
    -0.06
    _syn
    -0.06
    	back
    -0.06
     "@"
    -0.06
    reject
    -0.06
     zwar
    -0.06
     DPR
    -0.06
    POSITIVE LOGITS
     fabricated
    0.07
    Traditional
    0.07
    Popular
    0.06
    ön
    0.06
    äd
    0.06
     Hà
    0.06
    ่างประเทศ
    0.06
    erved
    0.06
     Mexican
    0.06
    localized
    0.06
    Act Density 0.000%

    No Known Activations