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

    Neuronpedia

    INDEX
    Explanations

    code/data identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قائمة
    -0.06
    ány
    -0.06
     Pert
    -0.06
    혀
    -0.06
     samp
    -0.06
     been
    -0.06
     Comey
    -0.06
     fired
    -0.06
     thresh
    -0.05
     Hungarian
    -0.05
    POSITIVE LOGITS
     ilgi
    0.07
    .photos
    0.07
    [block
    0.07
     largo
    0.07
    ).'</
    0.07
    143
    0.07
    銷
    0.06
    "profile
    0.06
    ?[
    0.06
    [token
    0.06
    Act Density 0.000%

    No Known Activations