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

    Neuronpedia

    INDEX
    Explanations

    logic, arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     많
    -0.08
    餐
    -0.07
    ştır
    -0.06
    _co
    -0.06
    -photo
    -0.06
     гла
    -0.06
     Supplements
    -0.06
    ammo
    -0.06
     speeches
    -0.06
     items
    -0.06
    POSITIVE LOGITS
    Writable
    0.07
     AFC
    0.07
     Buff
    0.07
    _MAT
    0.06
    _FWD
    0.06
    \CMS
    0.06
    退
    0.06
    _TMP
    0.06
    .asInstanceOf
    0.06
     रहत
    0.06
    Act Density 0.195%

    No Known Activations