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

    Neuronpedia

    INDEX
    Explanations

    programming language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ங்களை
    0.41
    ন্দের
    0.39
    ไหน
    0.39
     embossing
    0.39
    ائض
    0.39
     फैलाने
    0.39
    !";
    0.38
     Janus
    0.37
     traj
    0.36
     köt
    0.36
    POSITIVE LOGITS
    ﺔ
    0.37
     ,
    0.37
    iasco
    0.36
    ]
    0.35
    ۋ
    0.35
    lie
    0.35
     에
    0.34
    ifeng
    0.34
    }}.
    0.34
    க்கும்
    0.33
    Act Density 0.094%

    No Known Activations