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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leaflet
    -0.07
     konce
    -0.06
    /**<
    -0.06
     استاندارد
    -0.06
     performs
    -0.06
     край
    -0.06
    OMP
    -0.06
     entert
    -0.06
    ъ
    -0.06
     barrier
    -0.06
    POSITIVE LOGITS
    勇
    0.07
    =R
    0.07
    $n
    0.07
    agents
    0.07
    ünden
    0.07
    idle
    0.07
    став
    0.07
    Police
    0.07
    时代
    0.07
     Quyết
    0.06
    Act Density 0.000%

    No Known Activations