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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     chord
    -0.08
     <<-
    -0.07
     Emerson
    -0.06
     اب
    -0.06
     candid
    -0.06
    editar
    -0.06
     kannst
    -0.06
     edit
    -0.06
     cevap
    -0.06
    ать
    -0.06
    POSITIVE LOGITS
     탈
    0.07
     Thị
    0.07
     Sachs
    0.07
     Fired
    0.06
    人民共和国
    0.06
    Administration
    0.06
    �
    0.06
    	filter
    0.06
    Association
    0.06
    .Interface
    0.06
    Act Density 0.000%

    No Known Activations