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

    Neuronpedia

    INDEX
    Explanations

    ulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    545
    -0.07
     Sweep
    -0.07
    Revision
    -0.06
     nonlinear
    -0.06
    isci
    -0.06
    اران
    -0.06
     retire
    -0.06
    πουργ
    -0.06
    _keyword
    -0.06
    otropic
    -0.06
    POSITIVE LOGITS
     国产
    0.07
    	ll
    0.06
    _Output
    0.06
     vers
    0.06
    стич
    0.06
    .toolbar
    0.06
     пов
    0.06
    opt
    0.06
     _$
    0.06
     vấn
    0.06
    Act Density 0.002%

    No Known Activations