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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liner
    -0.08
    Train
    -0.07
    vio
    -0.07
    Clip
    -0.07
    department
    -0.06
    -three
    -0.06
    лен
    -0.06
     footprint
    -0.06
     acids
    -0.06
    fund
    -0.06
    POSITIVE LOGITS
     advant
    0.07
     Deniz
    0.06
    (pid
    0.06
    earch
    0.06
    /use
    0.06
     subur
    0.06
     SVC
    0.06
     دف
    0.06
    �璃
    0.06
     đúng
    0.06
    Act Density 0.054%

    No Known Activations