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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CMS
    -0.07
    /print
    -0.07
    άβ
    -0.06
    Aaron
    -0.06
     tear
    -0.06
    _NAMESPACE
    -0.06
    DDS
    -0.06
    HSV
    -0.06
    dí
    -0.06
    racial
    -0.06
    POSITIVE LOGITS
    .pay
    0.07
     Revolutionary
    0.07
    ~":"
    0.06
     Passenger
    0.06
    عد
    0.06
     еж
    0.06
    ‚Ì
    0.06
     Mavericks
    0.06
    ilters
    0.06
     Hexatrigesimal
    0.06
    Act Density 0.006%

    No Known Activations