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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peripherals
    -0.07
    暖
    -0.06
    ethe
    -0.06
     THERE
    -0.06
     pollen
    -0.06
    Party
    -0.06
    because
    -0.06
    kaar
    -0.06
    ointments
    -0.06
     THEY
    -0.06
    POSITIVE LOGITS
     {
↵
↵
↵
    0.07
     |
    0.07
    /end
    0.07
    	↵↵
    0.07
    ea
    0.06
    نه
    0.06
    ()
↵
↵
↵
    0.06
    exe
    0.06
     donating
    0.06
    فه
    0.06
    Act Density 0.131%

    No Known Activations