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

    Neuronpedia

    INDEX
    Explanations

    thus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bà
    -0.07
     Gä
    -0.07
    าการ
    -0.07
    women
    -0.07
     Paran
    -0.07
    ゲ
    -0.07
    endra
    -0.07
    entr
    -0.07
    Doing
    -0.07
    combe
    -0.07
    POSITIVE LOGITS
     Thus
    0.12
     thus
    0.11
    Thus
    0.11
    Us
    0.08
     Us
    0.08
    93
    0.08
    is
    0.08
     Lucas
    0.07
     Plus
    0.07
    izes
    0.07
    Act Density 0.012%

    No Known Activations