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

    Neuronpedia

    INDEX
    Explanations

    punctuation and stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vu
    -0.07
     fabs
    -0.07
     Decomp
    -0.06
    	va
    -0.06
    BUY
    -0.06
     müda
    -0.06
    반
    -0.06
    "]){↵
    -0.06
    _ste
    -0.06
     intervene
    -0.06
    POSITIVE LOGITS
     fragmentManager
    0.07
     Penguins
    0.07
    ATOM
    0.06
    やる夫
    0.06
     Conscious
    0.06
    _RDONLY
    0.06
     mixture
    0.06
     Holocaust
    0.06
     Port
    0.06
     garnered
    0.06
    Act Density 0.141%

    No Known Activations