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

    Neuronpedia

    INDEX
    Explanations

    Edison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    895
    -0.06
    Nor
    -0.06
     Internacional
    -0.06
    [A
    -0.06
     заходів
    -0.06
    �
    -0.06
    益
    -0.06
     AMS
    -0.06
     freopen
    -0.05
     слух
    -0.05
    POSITIVE LOGITS
     Edison
    0.11
     Romans
    0.07
    efeller
    0.07
     Advertising
    0.07
     Personal
    0.07
    connecting
    0.07
    utenberg
    0.07
     phải
    0.06
     dziew
    0.06
     Canvas
    0.06
    Act Density 0.003%

    No Known Activations