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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	number
    -0.06
     Before
    -0.06
    aa
    -0.06
    ecektir
    -0.06
    ября
    -0.06
    Exp
    -0.06
     corres
    -0.06
    bz
    -0.06
     FormBuilder
    -0.06
    olocation
    -0.06
    POSITIVE LOGITS
    uations
    0.07
    ivor
    0.07
    _refptr
    0.07
    _quant
    0.06
     bait
    0.06
    令人
    0.06
     الاع
    0.06
    -acre
    0.06
    inals
    0.06
    家
    0.06
    Act Density 0.047%

    No Known Activations