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

    Neuronpedia

    INDEX
    Explanations

    python

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stems
    -0.07
     elong
    -0.07
     propri
    -0.07
     hires
    -0.06
     amounted
    -0.06
     assume
    -0.06
    .Nil
    -0.06
    NORMAL
    -0.06
    masında
    -0.06
     earns
    -0.06
    POSITIVE LOGITS
    -TV
    0.08
     deed
    0.08
    CV
    0.08
    ospels
    0.07
    )data
    0.07
     تاریخی
    0.07
    (^)(
    0.07
    вид
    0.06
    (emp
    0.06
     يس
    0.06
    Act Density 0.004%

    No Known Activations