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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スカ
    -0.07
    omial
    -0.07
     영
    -0.06
    _prog
    -0.06
    /private
    -0.06
    吴
    -0.06
     문제
    -0.06
     Zhou
    -0.06
     GridLayout
    -0.06
    binary
    -0.06
    POSITIVE LOGITS
     here
    0.09
     there
    0.09
     HERE
    0.09
     below
    0.08
     above
    0.08
     Here
    0.07
     zde
    0.07
     There
    0.07
     فقد
    0.07
    .Here
    0.07
    Act Density 0.026%

    No Known Activations