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

    Neuronpedia

    INDEX
    Explanations

    hacker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    straight
    -0.07
    COME
    -0.07
    Fat
    -0.07
    加入
    -0.07
    Meeting
    -0.07
     بل
    -0.06
    %">↵
    -0.06
     RC
    -0.06
    благо
    -0.06
     благод
    -0.06
    POSITIVE LOGITS
     mapView
    0.08
    ktop
    0.07
     הז
    0.07
    ᵤ
    0.07
    (tuple
    0.07
    (des
    0.07
    믾
    0.07
    .optimize
    0.07
    .Keys
    0.06
    ?=
    0.06
    Act Density 0.001%

    No Known Activations