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

    Neuronpedia

    INDEX
    Explanations

    Failure to find something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MD
    -0.08
     Hearts
    -0.07
    منی
    -0.07
     сад
    -0.07
     exhibits
    -0.07
     army
    -0.06
    ุทธ
    -0.06
     意
    -0.06
    ],↵↵
    -0.06
    assert
    -0.06
    POSITIVE LOGITS
    exels
    0.06
     někdy
    0.06
     consolid
    0.06
    (dst
    0.06
     ticking
    0.06
    omain
    0.06
     انواع
    0.06
    ̀
    0.06
     hvad
    0.06
    (sw
    0.06
    Act Density 0.038%

    No Known Activations