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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terminate
    -0.07
    ctime
    -0.07
     commute
    -0.07
    .exit
    -0.07
     altura
    -0.07
    Break
    -0.07
     Іван
    -0.06
    те
    -0.06
    -IS
    -0.06
    _GROUP
    -0.06
    POSITIVE LOGITS
     dbs
    0.06
    .twitter
    0.06
     //↵
    0.06
     fraught
    0.06
     levy
    0.06
     isnt
    0.06
     venta
    0.06
     jim
    0.06
    ريل
    0.06
     clipped
    0.06
    Act Density 0.272%

    No Known Activations