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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and numbering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     npm
    -0.07
     acceptance
    -0.07
    pcodes
    -0.07
    <double
    -0.07
     Pune
    -0.07
     הקוד
    -0.07
    要考虑
    -0.07
    野外
    -0.07
     rempl
    -0.07
     gall
    -0.06
    POSITIVE LOGITS
    aminer
    0.07
    0.07
    ,_
    0.07
    -file
    0.07
    ointments
    0.07
     filmer
    0.06
     validator
    0.06
     IDirect
    0.06
    喵
    0.06
    	glog
    0.06
    Act Density 0.003%

    No Known Activations