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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相当
    -0.07
    rende
    -0.07
     zeigen
    -0.07
     disrupting
    -0.06
    sts
    -0.06
     Ad
    -0.06
    administration
    -0.06
     EVE
    -0.06
     dag
    -0.06
    Ad
    -0.06
    POSITIVE LOGITS
    gment
    0.07
     libido
    0.06
    ometr
    0.06
     COPYRIGHT
    0.06
    ::*
    0.06
    _logic
    0.06
     Wanted
    0.06
     reasoned
    0.06
    _DDR
    0.06
    (register
    0.06
    Act Density 0.016%

    No Known Activations