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

    Neuronpedia

    INDEX
    Explanations

    premise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zipcode
    -0.07
    شناس
    -0.06
    bidden
    -0.06
     municipal
    -0.06
    Forbidden
    -0.06
    جب
    -0.06
    енд
    -0.06
    coln
    -0.06
    olecular
    -0.06
    atoms
    -0.06
    POSITIVE LOGITS
     Rohingya
    0.07
     dve
    0.07
     Plaza
    0.07
    :o
    0.07
     ARGS
    0.06
     ICMP
    0.06
     anz
    0.06
     assumption
    0.06
     Οι
    0.06
     Mortgage
    0.06
    Act Density 0.005%

    No Known Activations