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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rá
    -0.07
    .vo
    -0.07
    瀬
    -0.07
     yol
    -0.07
    Login
    -0.06
     harek
    -0.06
     Victims
    -0.06
     obras
    -0.06
    	iVar
    -0.06
     Ukraj
    -0.06
    POSITIVE LOGITS
    ademic
    0.07
    inic
    0.07
     calidad
    0.07
     Analyst
    0.07
    Qualified
    0.07
    -quality
    0.07
    apeutic
    0.07
     Cit
    0.07
     qualifies
    0.07
     qualité
    0.07
    Act Density 0.008%

    No Known Activations