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

    Neuronpedia

    INDEX
    Explanations

    extraction and reaction procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Basics
    -0.07
    植树
    -0.07
    以
    -0.07
     subsidiary
    -0.07
     handmade
    -0.07
    辦理
    -0.07
    vari
    -0.07
    O
    -0.07
     биз
    -0.07
    同时也是
    -0.07
    POSITIVE LOGITS
    uya
    0.07
    ervative
    0.07
    vec
    0.07
    👇
    0.07
    vidia
    0.07
     rocky
    0.07
     pauses
    0.07
     vec
    0.06
     ambition
    0.06
     TextView
    0.06
    Act Density 0.036%

    No Known Activations