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

    Neuronpedia

    INDEX
    Explanations

    stare decisis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ta
    1.38
    daki
    1.17
    కు
    1.13
    𝐳
    1.11
    ti
    1.09
    tal
    1.09
    tede
    1.05
    tet
    1.02
    tf
    1.00
    ру
    0.99
    POSITIVE LOGITS
     \
    1.23
    IS
    1.06
    c
    1.04
    x
    1.03
    O
    1.00
    И
    0.96
    نی
    0.96
    ot
    0.95
     caves
    0.93
     avete
    0.91
    Act Density 0.000%

    No Known Activations