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

    Neuronpedia

    INDEX
    Explanations

    equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parameter
    -0.07
     vic
    -0.07
    Programming
    -0.06
     corn
    -0.06
    ibel
    -0.06
     INNER
    -0.06
    vají
    -0.06
    易
    -0.06
     wash
    -0.06
     chicken
    -0.06
    POSITIVE LOGITS
    mgr
    0.07
     erkek
    0.07
    Playing
    0.06
    []{↵
    0.06
    }}↵
    0.06
     newPos
    0.06
    返
    0.06
    즘
    0.06
    taboola
    0.06
    ινή
    0.06
    Act Density 0.010%

    No Known Activations