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
     робіт
    -0.08
     Ras
    -0.07
    线
    -0.06
    Gro
    -0.06
    vation
    -0.06
    Calibri
    -0.06
     repetitions
    -0.06
    給
    -0.06
     ミ
    -0.06
     probí
    -0.06
    POSITIVE LOGITS
     }],↵
    0.06
    "errors
    0.06
    setUp
    0.06
     SCH
    0.06
     praises
    0.06
     praised
    0.06
    idak
    0.06
    tains
    0.06
    __()↵
    0.06
    NSNumber
    0.06
    Act Density 0.000%

    No Known Activations