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

    Neuronpedia

    INDEX
    Explanations

    -up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ymin
    -0.07
    madığı
    -0.06
     Vibr
    -0.06
    객
    -0.06
    呈
    -0.06
    erge
    -0.06
    aida
    -0.06
    اج
    -0.06
    lerini
    -0.06
    less
    -0.06
    POSITIVE LOGITS
     tm
    0.07
     rats
    0.07
     Australians
    0.07
    luck
    0.06
    thanks
    0.06
    win
    0.06
     marg
    0.06
     champs
    0.06
    ccess
    0.06
     heartbreaking
    0.06
    Act Density 0.003%

    No Known Activations