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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patriot
    -0.07
    (return
    -0.06
     Appeal
    -0.06
     sidelines
    -0.06
     appealed
    -0.06
    (hr
    -0.06
    gment
    -0.06
     scalable
    -0.06
     stud
    -0.06
     Director
    -0.06
    POSITIVE LOGITS
    .Stage
    0.06
    .apply
    0.06
     sonunda
    0.06
    /edit
    0.06
     bikes
    0.06
    änn
    0.06
     keer
    0.06
    ?:
    0.06
    gray
    0.06
     Haziran
    0.06
    Act Density 0.009%

    No Known Activations