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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vrolet
    -0.07
    Diagram
    -0.06
    ablish
    -0.06
    Dirty
    -0.06
    оск
    -0.06
    ี้
    -0.06
    난
    -0.06
    小说
    -0.06
    Fair
    -0.06
    №
    -0.06
    POSITIVE LOGITS
    (mutex
    0.07
     vis
    0.07
    (op
    0.06
     #$
    0.06
     scarc
    0.06
     THROW
    0.06
     tinh
    0.06
    ))/(
    0.06
    	sem
    0.06
    du
    0.06
    Act Density 0.002%

    No Known Activations