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

    Neuronpedia

    INDEX
    Explanations

    Cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �数
    -0.07
     occupies
    -0.07
     quir
    -0.06
     �
    -0.06
    틴
    -0.06
     업데이트
    -0.06
    必须
    -0.06
    超
    -0.06
     �
    -0.06
    .Val
    -0.05
    POSITIVE LOGITS
     Solution
    0.07
     слыш
    0.06
     deceive
    0.06
    .image
    0.06
    Additional
    0.06
    Aspect
    0.06
    group
    0.06
    	create
    0.06
    .crypto
    0.06
     sorter
    0.06
    Act Density 0.092%

    No Known Activations