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

    Neuronpedia

    INDEX
    Explanations

    steps, movement, process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cone
    -0.07
     Price
    -0.07
     tuna
    -0.07
     Hemisphere
    -0.06
     veterans
    -0.06
     prostitutes
    -0.06
     panorama
    -0.06
    OldData
    -0.06
     Recipe
    -0.06
     Ohio
    -0.06
    POSITIVE LOGITS
    Copyright
    0.08
     فض
    0.07
     диаг
    0.07
    INCREMENT
    0.06
    .strictEqual
    0.06
    _parm
    0.06
     неж
    0.06
    	dp
    0.06
    。不
    0.06
    ौक
    0.06
    Act Density 0.096%

    No Known Activations