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

    Neuronpedia

    INDEX
    Explanations

    vit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .arange
    -0.07
    授
    -0.06
     disguised
    -0.06
     curtains
    -0.06
     subconscious
    -0.06
    емати
    -0.06
     conect
    -0.06
     kế
    -0.06
     прем
    -0.06
    	ff
    -0.05
    POSITIVE LOGITS
     Controlled
    0.06
     Integral
    0.06
    OrNil
    0.06
    的一
    0.06
    Today
    0.06
    .Token
    0.06
    teg
    0.06
    plete
    0.06
    RAM
    0.06
     prohibited
    0.06
    Act Density 0.000%

    No Known Activations