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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    autoreleasepool
    -0.07
    <hr
    -0.07
     fashionable
    -0.07
    исс
    -0.06
     Speaking
    -0.06
     includes
    -0.06
     undertaken
    -0.06
     也
    -0.06
     ấm
    -0.06
     куда
    -0.06
    POSITIVE LOGITS
    UNITY
    0.06
    _centers
    0.06
    $r
    0.06
    .sid
    0.06
    _AM
    0.06
     Potion
    0.06
    getRoot
    0.06
     CES
    0.06
    _led
    0.06
    _RD
    0.06
    Act Density 0.026%

    No Known Activations