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

    Neuronpedia

    INDEX
    Explanations

    corrosion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Severity
    -0.07
    and
    -0.06
     and
    -0.06
    TEXT
    -0.06
     discriminator
    -0.06
     Gur
    -0.06
    \Route
    -0.06
    our
    -0.06
    ्बर
    -0.06
    ازي
    -0.06
    POSITIVE LOGITS
     mmc
    0.07
     irgend
    0.07
    _infos
    0.07
     getUser
    0.07
    找
    0.06
     Thick
    0.06
     Ned
    0.06
    //-----------------------------------------------------------------------------↵
    0.06
     klient
    0.06
    .CopyTo
    0.06
    Act Density 0.275%

    No Known Activations