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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCE
    -0.06
     typ
    -0.06
    ウェ
    -0.06
     bard
    -0.06
     Stanford
    -0.06
    سم
    -0.06
     esac
    -0.06
     Libertarian
    -0.06
     Strange
    -0.06
     Cust
    -0.06
    POSITIVE LOGITS
     ingin
    0.07
     me
    0.07
     fotoğraf
    0.07
     yg
    0.07
     votre
    0.07
    atherine
    0.06
    ис
    0.06
    -к
    0.06
     us
    0.06
    нерг
    0.06
    Act Density 0.107%

    No Known Activations