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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CHUNK
    -0.07
    _SUPER
    -0.07
    	ep
    -0.06
    changer
    -0.06
    _saved
    -0.06
    _ops
    -0.06
    riding
    -0.06
    \Test
    -0.06
    formats
    -0.06
    \"");↵
    -0.06
    POSITIVE LOGITS
     phy
    0.08
     olmuştur
    0.07
    _easy
    0.07
     &
    0.06
    Gun
    0.06
     serta
    0.06
    امة
    0.06
     worth
    0.06
     mill
    0.06
     stab
    0.06
    Act Density 0.130%

    No Known Activations