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
    Philip
    -0.07
     you
    -0.06
    ]["
    -0.06
    =${
    -0.06
    _particle
    -0.06
    .Unlock
    -0.06
     templ
    -0.06
    _material
    -0.06
     Tues
    -0.06
     دقی
    -0.06
    POSITIVE LOGITS
    -plus
    0.07
    (Exception
    0.06
    (pro
    0.06
     RuntimeObject
    0.06
    促
    0.06
     Part
    0.06
    рач
    0.06
     původ
    0.06
     diseases
    0.06
     PE
    0.06
    Act Density 0.013%

    No Known Activations