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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    425
    -0.07
     Triangle
    -0.07
     AFP
    -0.07
    _selection
    -0.07
    <meta
    -0.06
     Patriots
    -0.06
    véd
    -0.06
     відкрит
    -0.06
    Barrier
    -0.06
    Problem
    -0.06
    POSITIVE LOGITS
    σουν
    0.07
    ونية
    0.06
    σε
    0.06
     depreci
    0.06
     Depending
    0.06
    usunda
    0.06
     maduras
    0.06
     атмос
    0.06
    ození
    0.06
    aż
    0.06
    Act Density 0.029%

    No Known Activations