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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pert
    -0.07
    /page
    -0.07
    216
    -0.06
    cookies
    -0.06
     jit
    -0.06
    ObjectOfType
    -0.06
    Deployment
    -0.06
    quot
    -0.06
    filtr
    -0.06
     ==========
    -0.06
    POSITIVE LOGITS
     стек
    0.07
    _found
    0.06
     büy
    0.06
     branded
    0.06
    特
    0.06
     LUA
    0.06
    有限
    0.06
     temel
    0.06
    附
    0.06
    _dst
    0.06
    Act Density 0.013%

    No Known Activations