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

    Neuronpedia

    INDEX
    Explanations

    Archaeology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deputy
    -0.07
     logistical
    -0.07
    (Data
    -0.07
    ULATION
    -0.07
     smarter
    -0.06
     Absolute
    -0.06
    Based
    -0.06
    conference
    -0.06
     ист
    -0.06
    National
    -0.06
    POSITIVE LOGITS
    مد
    0.07
    regist
    0.06
     gül
    0.06
    Weapon
    0.06
    еж
    0.06
     McL
    0.06
     yüzyıl
    0.06
     mů
    0.06
    ▍
    0.06
    _salt
    0.06
    Act Density 0.017%

    No Known Activations