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

    Neuronpedia

    INDEX
    Explanations

    rankings and winners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deep
    -0.07
     Fake
    -0.07
     Belize
    -0.07
    ITY
    -0.07
    洞
    -0.07
     Dry
    -0.07
     Ferr
    -0.07
     FI
    -0.07
    "]
    -0.06
     Compound
    -0.06
    POSITIVE LOGITS
    &type
    0.07
     حق
    0.07
     สม
    0.07
    /install
    0.06
     autogenerated
    0.06
     chlap
    0.06
    iseconds
    0.06
    (serial
    0.06
     contemplate
    0.06
     checkBox
    0.06
    Act Density 0.011%

    No Known Activations