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

    Neuronpedia

    INDEX
    Explanations

    apparatus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turning
    -0.07
     Manufact
    -0.07
    (cube
    -0.07
    ternal
    -0.06
    						
↵
    -0.06
     بخ
    -0.06
        	↵
    -0.06
    立刻
    -0.06
    (book
    -0.06
    (State
    -0.06
    POSITIVE LOGITS
    рг
    0.06
     Ultimately
    0.06
    ＜
    0.06
    �
    0.06
     NgModule
    0.06
    най
    0.06
    ']!='
    0.06
    んど
    0.06
    endir
    0.06
    outed
    0.06
    Act Density 0.147%

    No Known Activations