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

    Neuronpedia

    INDEX
    Explanations

    finding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umo
    -0.07
     amassed
    -0.06
    aru
    -0.06
    you
    -0.06
     questioning
    -0.06
     framebuffer
    -0.06
     bầu
    -0.06
     narrator
    -0.06
    ív
    -0.06
    .Enums
    -0.06
    POSITIVE LOGITS
     Gallery
    0.06
    цией
    0.06
     Rankings
    0.06
    integer
    0.06
     sesso
    0.06
     closeButton
    0.06
     playlist
    0.06
     Mein
    0.06
    -badge
    0.06
    centaje
    0.05
    Act Density 0.573%

    No Known Activations