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

    Neuronpedia

    INDEX
    Explanations

    once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	values
    -0.06
     IMS
    -0.06
    LM
    -0.06
     thighs
    -0.06
    .Sub
    -0.06
     Вал
    -0.06
     Crest
    -0.06
     кишеч
    -0.06
     LIGHT
    -0.06
     possession
    -0.06
    POSITIVE LOGITS
    /copyleft
    0.08
    ={()
    0.08
     subtitles
    0.06
    allel
    0.06
    ecycle
    0.06
     dan
    0.06
    ìn
    0.06
     onsite
    0.06
    Bindable
    0.06
     invaluable
    0.06
    Act Density 0.000%

    No Known Activations