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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ALA
    -0.07
     immigration
    -0.06
     eleven
    -0.06
     Angela
    -0.06
     ej
    -0.06
     Frances
    -0.06
     Municip
    -0.06
     stamps
    -0.06
     ------------------------------------------------
    -0.06
     Ramsey
    -0.06
    POSITIVE LOGITS
    ='<?
    0.07
     slab
    0.07
    辦
    0.06
    -project
    0.06
    .Per
    0.06
    ávě
    0.06
    -panel
    0.06
    εί
    0.06
    _ti
    0.06
    .getClass
    0.06
    Act Density 0.014%

    No Known Activations