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

    Neuronpedia

    INDEX
    Explanations

    reclusive, enclaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರವಾಗಿ
    0.29
    ون
    0.28
    కుంది
    0.27
    ങ്ങി
    0.26
    אות
    0.26
    лили
    0.26
     implicate
    0.26
     commer
    0.25
     रिएक्ट
    0.25
    하거나
    0.25
    POSITIVE LOGITS
    0.31
     {
    0.31
    0.31
    А
    0.29
    ụ
    0.29
     &
    0.28
            
    0.27
    References
    0.27
    У
    0.27
     О
    0.27
    Act Density 0.016%

    No Known Activations