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

    Neuronpedia

    INDEX
    Explanations

    laws/theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lt
    -0.07
    技能
    -0.07
     सत
    -0.07
    	array
    -0.06
    Rad
    -0.06
    ثیر
    -0.06
    %'↵
    -0.06
    _SAMPLE
    -0.06
    ्दर
    -0.06
    _PAD
    -0.06
    POSITIVE LOGITS
    _IMETHOD
    0.07
     thunk
    0.06
    =temp
    0.06
    _workflow
    0.06
     assistants
    0.06
    scribe
    0.06
     имеет
    0.06
     Estr
    0.06
     ARTICLE
    0.06
    _COLORS
    0.06
    Act Density 0.019%

    No Known Activations