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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vous
    -0.07
    restart
    -0.07
    xbc
    -0.07
    deen
    -0.06
    .clip
    -0.06
    222
    -0.06
    215
    -0.06
    ometrics
    -0.06
    mont
    -0.06
    اگ
    -0.06
    POSITIVE LOGITS
     inj
    0.07
     يتم
    0.07
    运
    0.06
     trä
    0.06
     œ
    0.06
    視
    0.06
    ạt
    0.06
     조
    0.06
     puppy
    0.06
     username
    0.06
    Act Density 0.022%

    No Known Activations