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

    Neuronpedia

    INDEX
    Explanations

    Birds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subtract
    -0.07
    chodu
    -0.07
    \">↵
    -0.06
     jspb
    -0.06
    prev
    -0.06
     bunny
    -0.06
    ी-
    -0.06
     قسم
    -0.06
     relev
    -0.06
    @store
    -0.06
    POSITIVE LOGITS
    reply
    0.06
     missile
    0.06
    (Vertex
    0.06
     ки
    0.06
     complained
    0.06
    jac
    0.06
     जब
    0.06
    فی
    0.06
     Although
    0.06
    .Future
    0.06
    Act Density 0.000%

    No Known Activations