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
    Really
    -0.07
    Њ
    -0.06
    итет
    -0.06
     Really
    -0.06
     euler
    -0.06
    _HI
    -0.06
     Baz
    -0.06
     refinement
    -0.06
    _fail
    -0.06
    chner
    -0.06
    POSITIVE LOGITS
    [__
    0.07
     cheese
    0.07
    .dependencies
    0.07
     Cheese
    0.06
    seat
    0.06
    -generator
    0.06
    ської
    0.06
     SHOP
    0.06
     impoverished
    0.06
    (reinterpret
    0.06
    Act Density 0.003%

    No Known Activations