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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    關注
    -0.07
    =_
    -0.07
    .endswith
    -0.07
    {l
    -0.07
    )t
    -0.07
     Cảnh
    -0.07
    ▿
    -0.07
    relu
    -0.06
    آخر
    -0.06
     Promise
    -0.06
    POSITIVE LOGITS
    Comp
    0.07
     disgr
    0.07
    ement
    0.07
     partido
    0.06
    iores
    0.06
     lowes
    0.06
    :Add
    0.06
    ment
    0.06
     rule
    0.06
    ethoven
    0.06
    Act Density 0.009%

    No Known Activations