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

    Neuronpedia

    INDEX
    Explanations

    tagged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anner
    -0.07
    switch
    -0.07
     Bones
    -0.07
     上
    -0.07
    nbr
    -0.07
    アー
    -0.06
    urances
    -0.06
    scape
    -0.06
     Sense
    -0.06
    clide
    -0.06
    POSITIVE LOGITS
     кип
    0.08
     Estr
    0.07
    刊
    0.06
     tagged
    0.06
    -independent
    0.06
    ,msg
    0.06
     LTD
    0.06
    	opt
    0.06
     dank
    0.06
    ',[
    0.06
    Act Density 0.000%

    No Known Activations