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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robber
    -0.07
    .Login
    -0.07
     Martinez
    -0.06
     id
    -0.06
     unseren
    -0.06
     scre
    -0.06
     veut
    -0.06
    -lg
    -0.06
    пра
    -0.06
     th�
    -0.06
    POSITIVE LOGITS
     constituent
    0.07
    飞
    0.06
    right
    0.06
     Monday
    0.06
    Ranked
    0.06
    στη
    0.06
    Submission
    0.06
     primary
    0.06
     '__
    0.06
     moment
    0.06
    Act Density 0.100%

    No Known Activations