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

    Neuronpedia

    INDEX
    Explanations

    _ALIGNMENT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chalk
    -0.06
    CppClass
    -0.06
    (norm
    -0.06
    �
    -0.06
     parliamentary
    -0.06
     bidi
    -0.06
     Českosloven
    -0.06
     ITE
    -0.06
     pseud
    -0.05
    seud
    -0.05
    POSITIVE LOGITS
    _MOBILE
    0.07
     ؟
    0.07
    _minute
    0.07
    ','','
    0.06
    lett
    0.06
     refunds
    0.06
    pad
    0.06
    loub
    0.06
     Merchant
    0.06
     Mu
    0.06
    Act Density 0.000%

    No Known Activations