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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Audio
    -0.07
    	process
    -0.07
     Orient
    -0.06
     racing
    -0.06
     slipping
    -0.06
     illuminate
    -0.06
    _bug
    -0.06
    <Test
    -0.06
     refreshed
    -0.06
    avicon
    -0.06
    POSITIVE LOGITS
     sarcast
    0.08
    postalcode
    0.07
     muschi
    0.07
     Algorithms
    0.06
    prt
    0.06
     alas
    0.06
     swingerclub
    0.06
     Tart
    0.06
     соч
    0.06
     Seb
    0.06
    Act Density 0.146%

    No Known Activations