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

    Neuronpedia

    INDEX
    Explanations

    medical symptoms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plateau
    -0.06
    istinguish
    -0.06
    arded
    -0.06
    .Preference
    -0.06
    ±ظ
    -0.06
     minor
    -0.06
    シア
    -0.06
     consistently
    -0.06
     Tits
    -0.06
     tower
    -0.06
    POSITIVE LOGITS
    UN
    0.07
    elog
    0.07
    -expand
    0.06
     listar
    0.06
    arah
    0.06
     t
    0.06
    .CR
    0.06
    teams
    0.06
     bölge
    0.06
    readcr
    0.06
    Act Density 0.296%

    No Known Activations