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

    Neuronpedia

    INDEX
    Explanations

    code testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inspired
    -0.08
    -tr
    -0.08
    -focused
    -0.08
    -du
    -0.07
     puissance
    -0.07
     votre
    -0.07
    راك
    -0.07
    oric
    -0.07
    -ro
    -0.07
    ook
    -0.07
    POSITIVE LOGITS
     correctly
    0.13
     korrekt
    0.11
     corretamente
    0.11
     correctamente
    0.10
    正确
    0.10
     incorrectly
    0.10
    correct
    0.09
    (correct
    0.09
     Incorrect
    0.09
     correto
    0.09
    Act Density 0.015%

    No Known Activations