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

    Neuronpedia

    INDEX
    Explanations

    em

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spatial
    -0.06
     معدن
    -0.06
     Bur
    -0.06
     CUT
    -0.06
    afort
    -0.06
     Possibly
    -0.06
     WAY
    -0.06
     欧
    -0.06
     Chop
    -0.06
    Crime
    -0.05
    POSITIVE LOGITS
    darwin
    0.07
    いて
    0.07
     busted
    0.07
     utter
    0.07
    амет
    0.06
     site
    0.06
     rebels
    0.06
    .CheckBox
    0.06
     injury
    0.06
     /^
    0.06
    Act Density 0.007%

    No Known Activations