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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OLD
    -0.07
    MarshalAs
    -0.07
     کوت
    -0.07
     sightings
    -0.06
    fts
    -0.06
    荷
    -0.06
     facilitated
    -0.06
    oupper
    -0.06
    اده
    -0.06
    .robot
    -0.06
    POSITIVE LOGITS
     começ
    0.07
    (lo
    0.06
    (SP
    0.06
    .The
    0.06
    .join
    0.06
    cox
    0.06
     національ
    0.06
    .enabled
    0.06
     backpack
    0.06
    -sp
    0.06
    Act Density 0.008%

    No Known Activations