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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Medium
    -0.06
     eş
    -0.06
    ξει
    -0.06
     заліз
    -0.06
     güzel
    -0.06
     Datos
    -0.06
     František
    -0.06
    edm
    -0.06
     Relay
    -0.06
    Reduc
    -0.06
    POSITIVE LOGITS
     imu
    0.07
    机
    0.06
     Julia
    0.06
    (Create
    0.06
    Around
    0.06
     bapt
    0.06
    ี
    0.06
    ends
    0.06
    MITTED
    0.06
    體
    0.06
    Act Density 0.024%

    No Known Activations