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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     συνο
    -0.07
    _ped
    -0.07
     UPC
    -0.07
     nominee
    -0.06
    .sa
    -0.06
    .'''↵
    -0.06
    ))/
    -0.06
     aio
    -0.06
     smb
    -0.06
    INU
    -0.06
    POSITIVE LOGITS
    лючается
    0.07
    ument
    0.06
     celebrating
    0.06
     getById
    0.06
    anim
    0.06
    CONDS
    0.06
     engineered
    0.06
    variably
    0.06
    ovalo
    0.06
    ovanou
    0.06
    Act Density 0.095%

    No Known Activations