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

    Neuronpedia

    INDEX
    Explanations

    inged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     careless
    -0.07
     mots
    -0.06
     raped
    -0.06
     누
    -0.06
    zero
    -0.06
     fortn
    -0.06
     य
    -0.06
     Addition
    -0.06
     advertisement
    -0.06
     fair
    -0.06
    POSITIVE LOGITS
    )||(
    0.07
    =BitConverter
    0.07
     Liga
    0.07
    semble
    0.06
    nums
    0.06
     mortgage
    0.06
    ournée
    0.06
    !)
    0.06
    ournaments
    0.06
    /h
    0.06
    Act Density 0.002%

    No Known Activations