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

    Neuronpedia

    INDEX
    Explanations

    entered/imposed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruled
    -0.07
     argues
    -0.07
    亨
    -0.07
     ioutil
    -0.07
     regulated
    -0.07
    oints
    -0.07
     Kind
    -0.07
    .opengl
    -0.06
    mode
    -0.06
    _CUBE
    -0.06
    POSITIVE LOGITS
     //{
↵
    0.09
    интер
    0.07
    powied
    0.07
     compra
    0.07
    _pri
    0.07
    キャラ
    0.07
    大巴
    0.07
    なか
    0.07
     thương
    0.07
    apot
    0.06
    Act Density 0.008%

    No Known Activations