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

    Neuronpedia

    INDEX
    Explanations

    software specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marks
    -0.07
    ﳎ
    -0.07
     Link
    -0.07
    样子
    -0.07
    ﻝ
    -0.06
    观摩
    -0.06
     presidency
    -0.06
     Donald
    -0.06
     prominence
    -0.06
    多么
    -0.06
    POSITIVE LOGITS
     customization
    0.07
    _air
    0.07
    �
    0.07
    .git
    0.07
     ergonomic
    0.07
    .setStatus
    0.06
    สำ
    0.06
    _double
    0.06
    _MON
    0.06
    cite
    0.06
    Act Density 0.611%

    No Known Activations