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

    Neuronpedia

    INDEX
    Explanations

    increasing costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    0.58
    en
    0.57
    ar
    0.56
    ing
    0.56
    un
    0.56
    an
    0.54
    re
    0.53
    er
    0.50
    len
    0.50
    in
    0.50
    POSITIVE LOGITS
     cận
    0.49
     vụ
    0.46
     Qd
    0.46
     આગળ
    0.46
     tôi
    0.45
     dẫn
    0.44
     slits
    0.44
     Vicar
    0.44
     cifras
    0.44
     করিলাম
    0.43
    Act Density 0.003%

    No Known Activations