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

    Neuronpedia

    INDEX
    Explanations

    corner

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bre
    -0.07
     плот
    -0.07
     Parkway
    -0.07
     vida
    -0.06
    시스
    -0.06
    	clear
    -0.06
     thật
    -0.06
     Spread
    -0.06
    第二大
    -0.06
    .vel
    -0.06
    POSITIVE LOGITS
    Neg
    0.08
    🖥
    0.08
     COLUMN
    0.07
    индивидуальн
    0.07
     erf
    0.07
     Processor
    0.07
     потребител
    0.07
    ièrement
    0.07
    发掘
    0.07
    indr
    0.07
    Act Density 0.009%

    No Known Activations