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

    Neuronpedia

    INDEX
    Explanations

    ssh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hombre
    -0.06
     Pond
    -0.06
     Bazı
    -0.06
     degrade
    -0.06
    аного
    -0.06
     Typed
    -0.06
     Nah
    -0.06
    lığın
    -0.06
    CustomerId
    -0.06
    čně
    -0.06
    POSITIVE LOGITS
    axon
    0.07
    셀
    0.07
    \R
    0.06
     resultat
    0.06
    险
    0.06
     chambers
    0.06
    ergus
    0.06
     Vox
    0.06
    Michelle
    0.06
     сред
    0.06
    Act Density 0.001%

    No Known Activations