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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pose
    -0.06
    так
    -0.06
     charg
    -0.06
    森
    -0.06
    ature
    -0.06
     violations
    -0.06
     FAC
    -0.06
     国家
    -0.06
     Spin
    -0.06
     вог
    -0.06
    POSITIVE LOGITS
    -meter
    0.07
    روش
    0.06
    .PI
    0.06
    ja
    0.06
    	cout
    0.06
     initWithFrame
    0.06
     linux
    0.06
     vys
    0.06
    名無し
    0.06
     století
    0.06
    Act Density 0.000%

    No Known Activations