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

    Neuronpedia

    INDEX
    Explanations

    ONY

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تقدم
    -0.07
    left
    -0.07
    application
    -0.07
     Pointer
    -0.07
     traffic
    -0.07
    帶著
    -0.07
    (access
    -0.07
    odge
    -0.07
    _defaults
    -0.07
    翕
    -0.07
    POSITIVE LOGITS
     unlawful
    0.07
    음
    0.07
    奖项
    0.07
     Sasha
    0.07
     resource
    0.07
     spacious
    0.06
     FORCE
    0.06
    おすす
    0.06
    �
    0.06
    -q
    0.06
    Act Density 0.001%

    No Known Activations