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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weaving
    -0.06
     Ranch
    -0.06
    chi
    -0.06
    ''.
    -0.06
     parity
    -0.06
    _bounds
    -0.06
     rnd
    -0.06
     robber
    -0.06
    kov
    -0.06
     ep
    -0.06
    POSITIVE LOGITS
    님이
    0.07
     заболеваний
    0.07
     живот
    0.07
    -sl
    0.06
     امکان
    0.06
     утеп
    0.06
    IVERY
    0.06
    -generic
    0.06
    แดง
    0.06
     concerned
    0.06
    Act Density 0.002%

    No Known Activations