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

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rivers
    -0.07
    umont
    -0.07
    ukan
    -0.06
     threw
    -0.06
    Di
    -0.06
    busy
    -0.06
    ogn
    -0.06
    apan
    -0.06
    fuse
    -0.06
    dom
    -0.06
    POSITIVE LOGITS
     др
    0.07
     manipulating
    0.07
    .Short
    0.07
    [J
    0.06
    Saga
    0.06
    jb
    0.06
     Iraq
    0.06
    	tb
    0.06
    _supported
    0.06
     Brittany
    0.06
    Act Density 0.001%

    No Known Activations