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

    Neuronpedia

    INDEX
    Explanations

    lawyers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [target
    -0.08
    	code
    -0.07
     Living
    -0.07
    /connect
    -0.07
    uario
    -0.07
    [input
    -0.07
     mạnh
    -0.07
    _cpu
    -0.07
     세계
    -0.07
     bộ
    -0.06
    POSITIVE LOGITS
     jacket
    0.06
    Bachelor
    0.06
     TypeInfo
    0.06
     Oakland
    0.06
     jackets
    0.06
     неиз
    0.06
     EOF
    0.06
     Florian
    0.06
     getElement
    0.06
     Bless
    0.05
    Act Density 0.015%

    No Known Activations