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

    Neuronpedia

    INDEX
    Explanations

    have you seen or read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज
    0.58
    U
    0.56
     veuillez
    0.55
    DIRECTION
    0.54
    মল
    0.54
    OWN
    0.53
    j
    0.52
    estion
    0.52
    जब
    0.52
    J
    0.52
    POSITIVE LOGITS
    បទ
    0.49
     stout
    0.49
     att
    0.48
     mani
    0.47
     pa
    0.47
     सुपारी
    0.47
    োপাধ্যা
    0.46
     interplay
    0.46
    sofar
    0.46
    ':
    0.45
    Act Density 0.008%

    No Known Activations