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

    Neuronpedia

    INDEX
    Explanations

    internal components descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disk
    -0.07
     Pierre
    -0.07
     condu
    -0.07
     Walker
    -0.07
    ีฟ
    -0.07
     accordingly
    -0.07
     negotiating
    -0.06
     Bodies
    -0.06
     disk
    -0.06
    宋
    -0.06
    POSITIVE LOGITS
    Weapon
    0.07
    	void
    0.06
     overdue
    0.06
     markup
    0.06
    valor
    0.06
    /manual
    0.06
    /go
    0.06
     ide
    0.06
     isEqual
    0.06
     CType
    0.06
    Act Density 0.013%

    No Known Activations