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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	version
    -0.07
    争
    -0.06
    門
    -0.06
     prostitutes
    -0.06
     vlastně
    -0.06
    さ
    -0.06
    .references
    -0.06
    话
    -0.06
     errorThrown
    -0.06
    	UPROPERTY
    -0.06
    POSITIVE LOGITS
     Kenya
    0.07
     §
    0.06
    Clients
    0.06
    kın
    0.06
    ення
    0.06
     cheesy
    0.06
    /↵
    0.06
     Chiến
    0.06
     Eis
    0.06
     Buyer
    0.06
    Act Density 0.000%

    No Known Activations