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

    Neuronpedia

    INDEX
    Explanations

    bearing failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ياس
    0.75
     forensics
    0.73
     conforto
    0.72
    颞
    0.72
     ее
    0.71
     '[
    0.70
     lentement
    0.70
    ア
    0.70
     координат
    0.69
     remarkably
    0.69
    POSITIVE LOGITS
    on
    0.89
    onin
    0.78
    onk
    0.77
    onka
    0.74
    bearing
    0.74
    rada
    0.73
    onica
    0.72
    vika
    0.72
    onaut
    0.71
    ن
    0.70
    Act Density 0.001%

    No Known Activations