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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     واح
    -0.06
     architekt
    -0.06
     송
    -0.06
     incompet
    -0.06
    _subtype
    -0.06
     умови
    -0.06
    Fr
    -0.06
    ynth
    -0.06
     ослож
    -0.06
    PropertyChanged
    -0.06
    POSITIVE LOGITS
     glove
    0.07
     لق
    0.07
     bears
    0.07
    Crypto
    0.07
    MODE
    0.06
    �
    0.06
     monster
    0.06
     AA
    0.06
    	pp
    0.06
    exports
    0.06
    Act Density 0.000%

    No Known Activations