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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ⓘ
    -0.07
     addons
    -0.07
    帰り
    -0.07
    .googlecode
    -0.07
    .End
    -0.06
     bian
    -0.06
     champs
    -0.06
    .surname
    -0.06
    =_('
    -0.06
    è
    -0.06
    POSITIVE LOGITS
     frequency
    0.08
    桴
    0.08
    回调
    0.07
     recovery
    0.07
    traffic
    0.07
    iteration
    0.07
    微生物
    0.07
    株
    0.07
     Kal
    0.07
    壶
    0.07
    Act Density 0.016%

    No Known Activations