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

    Neuronpedia

    INDEX
    Explanations

    end product/final stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    素敵
    -0.08
    耇
    -0.07
    ตำบล
    -0.07
    unded
    -0.07
     здоровья
    -0.07
    Documento
    -0.07
    心动
    -0.07
    安い
    -0.07
     ==============================================================
    -0.07
     Territories
    -0.07
    POSITIVE LOGITS
     Analog
    0.07
    市场的
    0.07
    对他
    0.07
     PL
    0.06
     plenty
    0.06
    理性
    0.06
     Ceiling
    0.06
     Similarly
    0.06
     Parallel
    0.06
    四种
    0.06
    Act Density 0.128%

    No Known Activations