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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilecek
    -0.07
     Injector
    -0.06
    _AUD
    -0.06
     bases
    -0.06
     centerpiece
    -0.06
    ifstream
    -0.06
    uvw
    -0.06
     fid
    -0.06
     самост
    -0.06
    Bean
    -0.06
    POSITIVE LOGITS
     expenses
    0.07
     generally
    0.07
     predict
    0.06
    维
    0.06
    イス
    0.06
     Cuban
    0.06
     Irene
    0.06
    ار
    0.06
    ISE
    0.06
     Memphis
    0.06
    Act Density 0.003%

    No Known Activations