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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ittance
    -0.06
     gc
    -0.06
     winters
    -0.06
     transformative
    -0.06
    .OP
    -0.06
     Kosovo
    -0.05
    elpers
    -0.05
    (encoder
    -0.05
    riteria
    -0.05
     propos
    -0.05
    POSITIVE LOGITS
     στον
    0.07
    ARENT
    0.07
     alarak
    0.07
     obraz
    0.07
     �
    0.06
     grandfather
    0.06
    (auth
    0.06
    express
    0.06
     prematurely
    0.06
     урож
    0.06
    Act Density 0.033%

    No Known Activations