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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    悪
    -0.07
    Verdana
    -0.07
    BackColor
    -0.07
    альных
    -0.06
     adjustments
    -0.06
     assaults
    -0.06
    อำนวย
    -0.06
    .encoding
    -0.06
     Emotional
    -0.06
    restriction
    -0.06
    POSITIVE LOGITS
     neglect
    0.07
    -ra
    0.07
     ^{↵
    0.07
    .Rollback
    0.06
     shrine
    0.06
     overweight
    0.06
     。↵
    0.06
     {[
    0.06
    .…
    0.06
    ="./
    0.06
    Act Density 0.001%

    No Known Activations