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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wat
    -0.07
     Shah
    -0.07
    ाह
    -0.07
    گرد
    -0.07
    AlmostEqual
    -0.06
    .normal
    -0.06
    ebp
    -0.06
    .mit
    -0.06
    wat
    -0.06
    ål
    -0.06
    POSITIVE LOGITS
    ，如
    0.06
    .Select
    0.06
     plunge
    0.06
    .answers
    0.06
    联合
    0.06
    Wonder
    0.06
     Hague
    0.06
    ]');↵
    0.06
    \Domain
    0.06
    根据
    0.05
    Act Density 0.001%

    No Known Activations