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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Whenever
    -0.07
    ाख
    -0.07
     coup
    -0.07
    VIEW
    -0.06
    Growing
    -0.06
     spectacular
    -0.06
    CONTROL
    -0.06
     "}\
    -0.06
     داخ
    -0.06
     approximation
    -0.06
    POSITIVE LOGITS
    peč
    0.07
     misogyn
    0.06
     XCTAssertEqual
    0.06
     #=>
    0.06
    .DAY
    0.06
    íd
    0.06
     Rid
    0.06
    ержав
    0.06
    Sher
    0.06
     supervisor
    0.06
    Act Density 0.341%

    No Known Activations