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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &quot
    -0.07
    xico
    -0.06
    ckett
    -0.06
    dire
    -0.06
     Zoe
    -0.06
    \uD
    -0.06
    Liquid
    -0.06
     Jul
    -0.06
    oyo
    -0.06
    -expand
    -0.06
    POSITIVE LOGITS
     furnished
    0.08
     البحر
    0.07
     учит
    0.07
     omitted
    0.06
    -hit
    0.06
     susceptible
    0.06
     readFile
    0.06
     cheated
    0.06
    (sid
    0.06
     tubes
    0.06
    Act Density 0.003%

    No Known Activations