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

    Neuronpedia

    INDEX
    Explanations

    {}

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mus
    -0.07
     brun
    -0.07
     Chin
    -0.07
    ons
    -0.07
     with
    -0.07
    ツ
    -0.07
     maintained
    -0.07
    แทน
    -0.07
     chor
    -0.07
    _chan
    -0.07
    POSITIVE LOGITS
    不小
    0.08
     {}
↵
    0.07
    liğe
    0.07
     {}↵
    0.07
     mümk
    0.07
    𝗴
    0.07
     {};
    0.07
     Beverage
    0.07
    השק
    0.07
     {},
    0.07
    Act Density 0.009%

    No Known Activations