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

    Neuronpedia

    INDEX
    Explanations

    breakdown/failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	old
    -0.07
    för
    -0.07
     �
    -0.07
    datepicker
    -0.07
    액
    -0.07
     thou
    -0.07
    /status
    -0.06
    .money
    -0.06
     الرمزية
    -0.06
    Sid
    -0.06
    POSITIVE LOGITS
     ger
    0.06
     Scan
    0.06
     [];
↵
    0.06
    ュ
    0.06
    !',
    0.06
     ресурс
    0.06
     �
    0.06
    lijah
    0.06
    SCREEN
    0.06
    ighth
    0.06
    Act Density 0.009%

    No Known Activations