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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qw
    -0.07
     geçen
    -0.07
     Benefits
    -0.07
    Cab
    -0.07
    Rect
    -0.07
    .reference
    -0.07
    .story
    -0.06
     último
    -0.06
     setTitle
    -0.06
    顾
    -0.06
    POSITIVE LOGITS
     dise
    0.07
     Dek
    0.06
     ANSI
    0.06
     stead
    0.06
     Sic
    0.05
     consolidation
    0.05
    eldig
    0.05
     dormant
    0.05
    _HOR
    0.05
     refund
    0.05
    Act Density 0.014%

    No Known Activations