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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PST
    -0.07
    嫌
    -0.07
     Env
    -0.06
    疗
    -0.06
    ?↵
    -0.06
    **
↵
    -0.06
    敬
    -0.06
    �
    -0.06
     کمک
    -0.06
     Πολ
    -0.06
    POSITIVE LOGITS
     signed
    0.07
    \Order
    0.06
    lf
    0.06
     Α
    0.06
     historia
    0.06
    τοι
    0.06
     عباس
    0.06
     Soros
    0.06
     medic
    0.06
     Oasis
    0.06
    Act Density 0.059%

    No Known Activations