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

    Neuronpedia

    INDEX
    Explanations

    Questions and instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     связи
    -0.07
    uddenly
    -0.07
    講
    -0.07
    一下子
    -0.07
    .visitVarInsn
    -0.07
    唯一
    -0.06
    viewer
    -0.06
    打卡
    -0.06
    ession
    -0.06
    ISA
    -0.06
    POSITIVE LOGITS
     mur
    0.07
    Arc
    0.07
     inject
    0.07
     Blueprint
    0.06
    /routes
    0.06
     \"%
    0.06
    Polygon
    0.06
    <Post
    0.06
    BO
    0.06
    (curl
    0.06
    Act Density 0.035%

    No Known Activations