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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    לוג
    -0.07
    	panel
    -0.07
    怀着
    -0.07
    ato
    -0.06
    小狗
    -0.06
     Vanderbilt
    -0.06
     opera
    -0.06
    aptop
    -0.06
     cookbook
    -0.06
    stderr
    -0.06
    POSITIVE LOGITS
     Crud
    0.08
    �
    0.07
    욧
    0.07
    бр
    0.07
     المر
    0.07
    粗糙
    0.07
    边缘
    0.07
    !".
    0.07
    뎠
    0.06
    	style
    0.06
    Act Density 0.052%

    No Known Activations