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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    领导班子
    -0.07
    _STACK
    -0.07
     unfavor
    -0.07
     shielding
    -0.07
    odega
    -0.07
    unn
    -0.07
    lässig
    -0.07
     Enh
    -0.07
    �
    -0.07
    _PRE
    -0.07
    POSITIVE LOGITS
    	endif
    0.07
     זה
    0.06
    orneys
    0.06
    车联网
    0.06
    אדם
    0.06
    Ars
    0.06
     familia
    0.06
    奧
    0.06
    ۉ
    0.06
     kb
    0.06
    Act Density 0.017%

    No Known Activations