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

    Neuronpedia

    INDEX
    Explanations

    002

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clement
    -0.07
    	true
    -0.07
    Bre
    -0.07
    ods
    -0.07
     Rotterdam
    -0.07
     sscanf
    -0.07
     Jenny
    -0.07
    ansa
    -0.06
     contentView
    -0.06
     정부
    -0.06
    POSITIVE LOGITS
     ділян
    0.07
    (act
    0.06
     корист
    0.06
    Symbol
    0.06
     reverted
    0.06
    .eq
    0.06
    ugh
    0.06
    ὸ
    0.06
     wrest
    0.06
     disclosures
    0.06
    Act Density 0.004%

    No Known Activations