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

    Neuronpedia

    INDEX
    Explanations

    legs of a right triangle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.66
    ),
    0.65
    ],
    0.64
    </b>
    0.64
    ];
    0.63
    );
    0.62
    _
    0.61
    ScheduledAction
    0.58
    archivo
    0.57
     මහ
    0.57
    POSITIVE LOGITS
     হইতেই
    0.56
    破解
    0.54
    みると
    0.54
    成果
    0.53
     عندهم
    0.53
     მათი
    0.53
    就是要
    0.53
    に変
    0.52
    𝙞
    0.52
    म
    0.52
    Act Density 0.001%

    No Known Activations