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

    Neuronpedia

    INDEX
    Explanations

    ING

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     över
    -0.07
    Putting
    -0.07
    fuck
    -0.07
     bubb
    -0.07
    🌐
    -0.07
     smiling
    -0.06
    hashed
    -0.06
    ksam
    -0.06
    /false
    -0.06
     Isn
    -0.06
    POSITIVE LOGITS
     Interface
    0.07
    Related
    0.07
     Village
    0.07
    梦见
    0.07
    .setSelection
    0.07
    代理
    0.07
     Sn
    0.07
    如此
    0.07
    鸡蛋
    0.07
    联系电话
    0.07
    Act Density 0.000%

    No Known Activations