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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gift
    -0.07
    Are
    -0.07
    ティ
    -0.07
     라이
    -0.06
    idents
    -0.06
    KT
    -0.06
    처
    -0.06
    ерів
    -0.06
     rooting
    -0.06
     BRAND
    -0.06
    POSITIVE LOGITS
     tedy
    0.08
     pedig
    0.07
    前往
    0.07
    redirectToRoute
    0.06
     Color
    0.06
    icontrol
    0.06
     عفش
    0.06
    ुम
    0.06
     punitive
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations