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

    Neuronpedia

    INDEX
    Explanations

    names of authors and scientists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     executable
    0.51
     adaptable
    0.47
     digits
    0.46
     unsolicited
    0.44
     adapters
    0.44
     interdependent
    0.43
     enca
    0.42
     acorns
    0.42
     modes
    0.42
     moose
    0.42
    POSITIVE LOGITS
     Zhang
    1.01
     Rodriguez
    0.97
     Rodríguez
    0.97
     Wang
    0.97
     Fernandez
    0.92
     Liu
    0.90
     Lopez
    0.90
     Huang
    0.90
     Gonzalez
    0.90
    Martinez
    0.90
    Act Density 0.042%

    No Known Activations