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

    Neuronpedia

    INDEX
    Explanations

    -type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    듦
    -0.07
    廷
    -0.07
    颦
    -0.07
    肪
    -0.07
    �
    -0.07
    海运
    -0.07
    	array
    -0.06
    �
    -0.06
     ingen
    -0.06
    Span
    -0.06
    POSITIVE LOGITS
     ()=>{↵
    0.07
     aunt
    0.07
    )=>{↵
    0.07
    ])){↵
    0.07
    "){
↵
    0.07
     เป
    0.07
     Comparator
    0.07
    אופ
    0.07
    _med
    0.07
    бар
    0.07
    Act Density 0.001%

    No Known Activations