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

    Neuronpedia

    INDEX
    Explanations

    The Union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hai
    -0.07
     нег
    -0.06
    це
    -0.06
     interpersonal
    -0.06
     khỏi
    -0.06
    Spo
    -0.06
    strukce
    -0.06
    _staff
    -0.06
     शहर
    -0.06
     آنها
    -0.06
    POSITIVE LOGITS
    _opt
    0.07
     elic
    0.07
    pol
    0.06
     lessons
    0.06
     mixed
    0.06
     найкра
    0.06
     Tax
    0.06
    ής
    0.06
    .dt
    0.06
    /power
    0.06
    Act Density 0.018%

    No Known Activations