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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ㅇㅇ
    -0.07
     uží
    -0.07
    Prostit
    -0.07
    τέλε
    -0.07
    aph
    -0.07
     zb
    -0.06
    dě
    -0.06
     Hra
    -0.06
     strstr
    -0.06
    *=*=
    -0.06
    POSITIVE LOGITS
    败
    0.07
     Olympic
    0.07
     diaper
    0.07
     Fry
    0.07
    -driving
    0.06
    .padding
    0.06
    ilage
    0.06
    炸
    0.06
     Adolescent
    0.06
    ancock
    0.06
    Act Density 0.003%

    No Known Activations