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

    Neuronpedia

    INDEX
    Explanations

    describing something's characteristics

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    _Tool
    -0.07
     Thema
    -0.07
     tip
    -0.07
    Ready
    -0.07
    _student
    -0.06
     touchscreen
    -0.06
    connect
    -0.06
    mostat
    -0.06
    mile
    -0.06
     WALL
    -0.06
    POSITIVE LOGITS
     أعلن
    0.07
     predicted
    0.07
    >{{$
    0.07
     "**
    0.07
    uya
    0.07
    ossa
    0.07
    ។
    0.06
     "";↵↵
    0.06
    黎明
    0.06
    ">{{
    0.06
    Act Density 0.150%

    No Known Activations