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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mourning
    -0.07
     هج
    -0.07
     演
    -0.06
     ############
    -0.06
     companions
    -0.06
    Serializer
    -0.06
     ✓
    -0.06
    asions
    -0.06
    _EX
    -0.06
     Jason
    -0.06
    POSITIVE LOGITS
     rematch
    0.06
    mayacak
    0.06
    flag
    0.06
    ucceed
    0.06
    んど
    0.06
    -derived
    0.06
     پزشکی
    0.06
     začal
    0.06
    iad
    0.06
     Neville
    0.06
    Act Density 0.249%

    No Known Activations