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

    Neuronpedia

    INDEX
    Explanations

    Misspellings and unusual words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Energy
    -0.08
     energy
    -0.07
     biome
    -0.07
    6
    -0.07
     in
    -0.07
    26
    -0.06
    ۲
    -0.06
     بزرگ
    -0.06
     Eric
    -0.06
     ego
    -0.06
    POSITIVE LOGITS
    tt
    0.12
    ff
    0.11
    LL
    0.10
    ll
    0.10
     Hann
    0.10
    att
    0.10
     Batt
    0.10
    SS
    0.10
    ill
    0.10
    ell
    0.10
    Act Density 0.680%

    No Known Activations