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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Doug
    -0.08
    yth
    -0.07
    给予了
    -0.07
    �
    -0.06
    כאב
    -0.06
     ########
    -0.06
    فر
    -0.06
    QUESTION
    -0.06
     desn
    -0.06
     Boyd
    -0.06
    POSITIVE LOGITS
     fifty
    0.07
    ᵎ
    0.07
    	AM
    0.07
    Story
    0.07
     intestine
    0.07
    𬙊
    0.06
    峰会
    0.06
     ayrıca
    0.06
    IRO
    0.06
    itelist
    0.06
    Act Density 0.023%

    No Known Activations