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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &'
    -0.07
     revealed
    -0.06
    beck
    -0.06
     Фран
    -0.06
    ANTI
    -0.06
     npm
    -0.06
     mov
    -0.06
     UIAlert
    -0.06
    _SMALL
    -0.06
    npm
    -0.06
    POSITIVE LOGITS
    ữu
    0.06
    .isActive
    0.06
    {return
    0.06
     Default
    0.06
    viso
    0.06
    orrh
    0.06
    vais
    0.06
     unwanted
    0.06
     mined
    0.05
     opět
    0.05
    Act Density 0.130%

    No Known Activations