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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缩水
    -0.08
    zien
    -0.08
     ABS
    -0.07
     recon
    -0.07
    ിഎ
    -0.07
     betroffen
    -0.07
    成本
    -0.07
    slave
    -0.07
    -medium
    -0.07
    ABS
    -0.07
    POSITIVE LOGITS
     星
    0.13
     astronom
    0.13
     星空
    0.12
     celestial
    0.12
     सित
    0.12
     તાર
    0.11
     étoiles
    0.11
     estrellas
    0.11
     estrelas
    0.11
     astronomy
    0.11
    Act Density 0.050%

    No Known Activations