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

    Neuronpedia

    INDEX
    Explanations

    via

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -expanded
    -0.07
     IQueryable
    -0.07
    IllegalAccessException
    -0.07
    tgl
    -0.06
    ffee
    -0.06
     Tiểu
    -0.06
     internationally
    -0.06
     особи
    -0.06
    λέον
    -0.06
     од
    -0.06
    POSITIVE LOGITS
    -mask
    0.07
     용
    0.07
    ink
    0.07
    drivers
    0.06
     Disney
    0.06
    assign
    0.06
     Connectivity
    0.06
    anchise
    0.06
    χε
    0.06
    cribing
    0.06
    Act Density 0.000%

    No Known Activations