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

    Neuronpedia

    INDEX
    Explanations

    j

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VLC
    -0.07
     Navbar
    -0.07
    .nl
    -0.07
    чу
    -0.07
    .Password
    -0.06
     Followers
    -0.06
     Calder
    -0.06
     Mitarbeiter
    -0.06
     cerc
    -0.06
     HMS
    -0.06
    POSITIVE LOGITS
    ेशन
    0.06
     types
    0.06
                 ↵
    0.06
     centr
    0.06
    クト
    0.06
     Low
    0.06
     slova
    0.06
     genetically
    0.06
     banquet
    0.06
     ense
    0.06
    Act Density 0.012%

    No Known Activations