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

    Neuronpedia

    INDEX
    Explanations

    document fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awakened
    -0.06
     Woj
    -0.06
    -vis
    -0.06
     gösterir
    -0.06
     stepper
    -0.06
    EHICLE
    -0.06
    (scope
    -0.06
     Mush
    -0.05
     colleg
    -0.05
     вар
    -0.05
    POSITIVE LOGITS
    τρ
    0.07
    .readline
    0.06
    \views
    0.06
     qx
    0.06
    halb
    0.06
    onec
    0.06
     Xunit
    0.06
    hta
    0.06
    โปรแกรม
    0.06
    ologic
    0.06
    Act Density 0.000%

    No Known Activations