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

    Neuronpedia

    INDEX
    Explanations

    say "rats"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sustainability
    -0.06
    _strerror
    -0.06
    -bs
    -0.06
    WO
    -0.06
     HO
    -0.06
    .write
    -0.06
     mayoría
    -0.06
     recently
    -0.06
    Summary
    -0.06
     соверш
    -0.05
    POSITIVE LOGITS
    ACING
    0.07
    λύ
    0.07
     Gover
    0.06
     sketch
    0.06
     عوامل
    0.06
    گوی
    0.06
    ωσε
    0.06
     boş
    0.06
     }}">{{
    0.06
     Böl
    0.06
    Act Density 0.001%

    No Known Activations