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

    Neuronpedia

    INDEX
    Explanations

    New Hampshire locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
                         ↵
    -0.08
     Adults
    -0.07
     时间
    -0.06
    י�
    -0.06
    ière
    -0.06
    ponses
    -0.06
    　　　　　　　　　　　　　　
    -0.06
    ега
    -0.06
    archive
    -0.06
    含
    -0.06
    POSITIVE LOGITS
    .ins
    0.07
     Hast
    0.06
    -redux
    0.06
    panic
    0.06
    _LS
    0.06
     scrambling
    0.06
     neh
    0.06
    ,''
    0.06
    .refs
    0.06
     unlikely
    0.06
    Act Density 0.019%

    No Known Activations