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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DV
    -0.07
    _PARSE
    -0.07
    _LICENSE
    -0.06
    .heap
    -0.06
    ,e
    -0.06
     Carpenter
    -0.06
    anneer
    -0.06
    mos
    -0.06
     Reform
    -0.06
    бач
    -0.06
    POSITIVE LOGITS
     seaborn
    0.07
    vní
    0.07
    مم
    0.07
     retirees
    0.06
     lyrics
    0.06
    alten
    0.06
    owy
    0.06
    包含
    0.06
     unified
    0.06
    ��
    0.06
    Act Density 0.031%

    No Known Activations