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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    袁
    -0.08
     к
    -0.07
    ⋆
    -0.06
     ít
    -0.06
    blr
    -0.06
    实际上
    -0.06
     о
    -0.06
     ih
    -0.06
    引擎
    -0.06
     أن
    -0.06
    POSITIVE LOGITS
    团体
    0.07
     NUMBER
    0.07
     granny
    0.07
    phan
    0.07
    onian
    0.07
    _district
    0.07
    	head
    0.06
     anarch
    0.06
    .Node
    0.06
     Российской
    0.06
    Act Density 0.056%

    No Known Activations