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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Todo
    -0.07
    Funny
    -0.06
    	require
    -0.06
     TSA
    -0.06
     ropes
    -0.06
    generator
    -0.06
    อน
    -0.06
    763
    -0.06
     Sh
    -0.06
    Kir
    -0.06
    POSITIVE LOGITS
     dří
    0.08
    thern
    0.06
    _inp
    0.06
     sensory
    0.06
    accur
    0.06
     Guerr
    0.06
     average
    0.06
    reatest
    0.06
     Easily
    0.06
     optimum
    0.06
    Act Density 0.006%

    No Known Activations