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

    Neuronpedia

    INDEX
    Explanations

    label

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Authorization
    -0.08
    @\
    -0.07
    ={$
    -0.07
     Kit
    -0.07
     ratio
    -0.06
     Prostitutas
    -0.06
    reader
    -0.06
    ி�
    -0.06
    #
    -0.06
    .AnchorStyles
    -0.06
    POSITIVE LOGITS
     кор
    0.07
     harsh
    0.07
     perg
    0.06
     Sail
    0.06
    \'
    0.06
    ıza
    0.06
     upsetting
    0.06
     flashing
    0.06
     pě
    0.06
     informat
    0.06
    Act Density 0.007%

    No Known Activations