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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     बिक्री
    -0.08
     rápidas
    -0.08
     Gestaltung
    -0.07
     verkauft
    -0.07
     siph
    -0.07
     अभियान
    -0.07
     claras
    -0.07
     sure
    -0.07
     järgi
    -0.07
     gestalt
    -0.07
    POSITIVE LOGITS
     amis
    0.09
    �
    0.08
    ={<
    0.08
     Slice
    0.08
     Bryce
    0.07
     Lights
    0.07
    \App
    0.07
     Monad
    0.07
    (slice
    0.07
     loka
    0.07
    Act Density 0.002%

    No Known Activations