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

    Neuronpedia

    INDEX
    Explanations

    technical contexts and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berarti
    0.75
     predictions
    0.73
     thr
    0.70
     hoteles
    0.66
     Somehow
    0.65
    റു
    0.65
     whipping
    0.65
     thay
    0.64
     saiu
    0.64
     BufferedReader
    0.63
    POSITIVE LOGITS
    прият
    0.70
    Mich
    0.70
    शरी
    0.67
     Mountain
    0.67
     OSHA
    0.67
    Mountain
    0.66
     Leap
    0.64
    পাল
    0.63
    隕
    0.63
     كن
    0.62
    Act Density 0.000%

    No Known Activations