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

    Neuronpedia

    INDEX
    Explanations

    place

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coconut
    -0.07
    NIEnv
    -0.07
    conut
    -0.07
    (numpy
    -0.07
    ⓡ
    -0.07
    ונג
    -0.07
    生素
    -0.07
     Newtown
    -0.06
    Nature
    -0.06
    几率
    -0.06
    POSITIVE LOGITS
    curso
    0.07
    .clip
    0.07
    说话
    0.07
    站着
    0.06
    (CL
    0.06
    이라고
    0.06
     navigate
    0.06
    link
    0.06
    在一
    0.06
     shirt
    0.06
    Act Density 0.031%

    No Known Activations