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

    Neuronpedia

    INDEX
    Explanations

    low

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    644
    -0.07
     Všech
    -0.07
    iful
    -0.06
     Fakat
    -0.06
     umíst
    -0.06
     isSuccess
    -0.06
    君
    -0.06
    Instances
    -0.06
    晶
    -0.06
     дру
    -0.06
    POSITIVE LOGITS
     astounding
    0.07
     Fn
    0.07
     foil
    0.07
     opener
    0.07
    entry
    0.07
     Voyage
    0.06
    Extras
    0.06
     enlightenment
    0.06
    []){↵
    0.06
     preparations
    0.06
    Act Density 0.005%

    No Known Activations