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

    Neuronpedia

    INDEX
    Explanations

    rumors and reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     six
    -0.07
     think
    -0.07
    neighbors
    -0.06
    Kate
    -0.06
    Jar
    -0.06
    _Red
    -0.06
     мис
    -0.06
     ['#
    -0.06
    เซ
    -0.06
     bartender
    -0.06
    POSITIVE LOGITS
     Wisconsin
    0.06
    321
    0.06
     MU
    0.06
    เทคโนโลย
    0.06
    oriasis
    0.06
    бря
    0.06
    ....
    0.06
     рассказ
    0.06
    resses
    0.06
    	Iterator
    0.06
    Act Density 0.074%

    No Known Activations