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

    Neuronpedia

    INDEX
    Explanations

    Although

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wikipedia
    -0.07
     Barr
    -0.06
     pirates
    -0.06
    _port
    -0.06
    lerine
    -0.06
    oration
    -0.06
    WEST
    -0.06
    urgeon
    -0.06
    (container
    -0.06
    icum
    -0.06
    POSITIVE LOGITS
    (Guid
    0.08
     Fil
    0.07
     ak
    0.07
     anlayış
    0.06
     vip
    0.06
     симптом
    0.06
    ไป
    0.06
     belirtilen
    0.06
     olmadığını
    0.06
     Ell
    0.06
    Act Density 0.022%

    No Known Activations