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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reiben
    -0.07
     Ko
    -0.07
    -fe
    -0.07
     Proc
    -0.06
     facebook
    -0.06
     geme
    -0.06
     plastics
    -0.06
    िथ
    -0.06
     creep
    -0.06
    ocado
    -0.06
    POSITIVE LOGITS
    :;↵
    0.07
    _owned
    0.06
    imestep
    0.06
    :"",↵
    0.06
     فس
    0.06
    esper
    0.06
     gboolean
    0.06
     bowed
    0.06
     rval
    0.06
    .getSimpleName
    0.06
    Act Density 0.021%

    No Known Activations