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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ONLINE
    -0.07
     Ny
    -0.07
    St
    -0.07
     trở
    -0.06
    егодня
    -0.06
     ensured
    -0.06
    íte
    -0.06
     fungal
    -0.06
     न
    -0.06
    OU
    -0.06
    POSITIVE LOGITS
    +'_
    0.07
     closeModal
    0.06
     Unified
    0.06
    aupt
    0.06
    Bezier
    0.06
     extrem
    0.06
    内容
    0.06
    ]){↵
    0.06
    tuğ
    0.06
    až
    0.06
    Act Density 0.013%

    No Known Activations