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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     어�
    -0.06
    ového
    -0.06
     Beginner
    -0.06
     rockets
    -0.06
     smoothing
    -0.06
    实在
    -0.06
    upe
    -0.06
    utility
    -0.06
     Silver
    -0.06
    lagen
    -0.05
    POSITIVE LOGITS
     esac
    0.06
     enlist
    0.06
     Louisiana
    0.06
     friend
    0.06
     progen
    0.06
    궁
    0.06
    +offset
    0.06
     honored
    0.06
    ngör
    0.06
    支援
    0.06
    Act Density 0.029%

    No Known Activations