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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dst
    -0.07
    inst
    -0.07
    itz
    -0.07
    	draw
    -0.07
     관
    -0.06
     mant
    -0.06
    enced
    -0.06
    _ADV
    -0.06
     bow
    -0.06
    ADE
    -0.06
    POSITIVE LOGITS
    输入
    0.07
    па
    0.07
     giả
    0.07
     Inputs
    0.06
     -*
    0.06
    Validator
    0.06
     input
    0.06
     Ð
    0.06
     输入
    0.06
    "]
↵
    0.06
    Act Density 0.031%

    No Known Activations