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

    Neuronpedia

    INDEX
    Explanations

    discussions and reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    965
    -0.07
    Att
    -0.06
    _cb
    -0.06
     defiant
    -0.06
     addTo
    -0.06
    :P
    -0.06
     Ping
    -0.06
     곧
    -0.06
    _DRIVE
    -0.06
     Printed
    -0.06
    POSITIVE LOGITS
    olg
    0.07
    inia
    0.06
    <algorithm
    0.06
     Description
    0.06
     vej
    0.06
    _System
    0.06
    الا
    0.06
    htar
    0.06
    layarak
    0.06
    ifs
    0.06
    Act Density 0.050%

    No Known Activations