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

    Neuronpedia

    INDEX
    Explanations

    bounded

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Feed
    -0.07
    "@
    -0.06
     trailers
    -0.06
     Forgotten
    -0.06
    для
    -0.06
    .machine
    -0.06
     Snowden
    -0.06
     Save
    -0.06
     Laz
    -0.06
     شماره
    -0.06
    POSITIVE LOGITS
     bureaucr
    0.07
     EG
    0.07
    seg
    0.07
    _rel
    0.06
     ек
    0.06
    /red
    0.06
    [ch
    0.06
     limite
    0.06
    Reg
    0.06
    allet
    0.06
    Act Density 0.004%

    No Known Activations