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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cnt
    -0.07
     treffen
    -0.07
    	call
    -0.06
     info
    -0.06
     bra
    -0.06
     analy
    -0.06
     stories
    -0.06
     newX
    -0.06
     discomfort
    -0.06
    .ap
    -0.06
    POSITIVE LOGITS
     Mö
    0.06
    ORK
    0.06
    .WRITE
    0.06
    CONN
    0.06
     默认
    0.06
     Noticed
    0.06
    ازی
    0.06
    َق
    0.06
    <unsigned
    0.06
     mycket
    0.06
    Act Density 0.085%

    No Known Activations