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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gem
    -0.07
     retire
    -0.06
     Ralph
    -0.06
     SetProperty
    -0.06
    var
    -0.06
    �
    -0.06
    座
    -0.06
    列车
    -0.06
    bew
    -0.06
    .google
    -0.06
    POSITIVE LOGITS
    	esc
    0.07
    ainting
    0.07
     prolong
    0.07
     SHE
    0.07
     blurry
    0.07
    剂量
    0.07
    噀
    0.07
     civilian
    0.07
    (([
    0.07
    	Namespace
    0.07
    Act Density 0.008%

    No Known Activations