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

    Neuronpedia

    INDEX
    Explanations

    Literary analysis/excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’en
    -0.07
     formulation
    -0.06
    める
    -0.06
     derivative
    -0.06
     bilingual
    -0.06
     Pediatric
    -0.06
     somewhere
    -0.06
     solar
    -0.06
     Thou
    -0.06
    .shared
    -0.06
    POSITIVE LOGITS
    ?action
    0.06
    谋
    0.06
    .minecraftforge
    0.06
    وفي
    0.06
    τεί
    0.06
     تفاوت
    0.06
     سوم
    0.06
    Rob
    0.05
    尼亚
    0.05
     vlád
    0.05
    Act Density 0.052%

    No Known Activations