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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spy
    -0.07
    .docs
    -0.07
    .Rest
    -0.06
     QStringLiteral
    -0.06
     awhile
    -0.06
     Wilderness
    -0.06
    Buy
    -0.06
    LocalizedString
    -0.06
     ceny
    -0.06
    References
    -0.06
    POSITIVE LOGITS
     upper
    0.07
     adjustable
    0.06
     maths
    0.06
     Barrier
    0.06
     grilled
    0.06
     bast
    0.06
     Errors
    0.06
     قهر
    0.06
     Self
    0.06
     embedded
    0.06
    Act Density 0.010%

    No Known Activations