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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Later
    -0.07
    ，然后
    -0.07
    History
    -0.07
    etype
    -0.07
    /AIDS
    -0.06
     COOKIE
    -0.06
     Sentinel
    -0.06
    .with
    -0.06
     has
    -0.06
    terminate
    -0.06
    POSITIVE LOGITS
    tog
    0.06
    _nc
    0.06
    slashes
    0.06
    _RG
    0.06
     logarith
    0.06
    yo
    0.06
    osaur
    0.06
    fore
    0.06
    odable
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations