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

    Neuronpedia

    INDEX
    Explanations

    interviews, job, front wheels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ി
    0.82
    ності
    0.81
    ர
    0.78
    *
    0.77
    Д
    0.77
    椑
    0.76
    Za
    0.76
                    
    0.75
    л
    0.75
    身材
    0.75
    POSITIVE LOGITS
     equipes
    0.95
     ocen
    0.94
     eagles
    0.90
     Ủy
    0.88
     учены
    0.86
     enlaces
    0.86
     descub
    0.84
     étab
    0.81
    ंडल
    0.80
     أيضاً
    0.80
    Act Density 0.007%

    No Known Activations