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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alic
    -0.06
    ，有
    -0.06
    (car
    -0.06
    ipe
    -0.06
    -A
    -0.06
     проб
    -0.06
    utive
    -0.06
     diesen
    -0.05
    Death
    -0.05
     Collision
    -0.05
    POSITIVE LOGITS
     стар
    0.08
     trì
    0.07
    .xaml
    0.07
     GLUT
    0.06
    签
    0.06
    .gridColumn
    0.06
    导
    0.06
     mug
    0.06
    .Fatalf
    0.06
    ,length
    0.06
    Act Density 0.000%

    No Known Activations