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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ulus
    -0.08
     several
    -0.07
    locs
    -0.07
    682
    -0.07
     conservative
    -0.06
    ♥
    -0.06
    .launch
    -0.06
    密
    -0.06
    Inst
    -0.06
     rug
    -0.06
    POSITIVE LOGITS
    xAD
    0.06
     deceive
    0.06
     firefighters
    0.06
    \Component
    0.06
    imestep
    0.06
     dumpsters
    0.06
     onChanged
    0.06
    	comment
    0.06
    .hh
    0.06
    dynamic
    0.06
    Act Density 0.003%

    No Known Activations