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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бі
    -0.07
     Kop
    -0.06
    มต
    -0.06
    Ul
    -0.06
     Hib
    -0.06
    Film
    -0.06
    stk
    -0.05
    llu
    -0.05
     외
    -0.05
     Ek
    -0.05
    POSITIVE LOGITS
     userdata
    0.07
     podcast
    0.07
     multiplication
    0.07
     credentials
    0.07
     nécess
    0.07
     authority
    0.06
     sensitive
    0.06
     coun
    0.06
     conseils
    0.06
     teşekkür
    0.06
    Act Density 0.031%

    No Known Activations