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

    Neuronpedia

    INDEX
    Explanations

    "; Expression"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pelvis
    0.44
    wegs
    0.42
    에서의
    0.42
     détermin
    0.41
     tableaux
    0.41
     photospheric
    0.41
    meleri
    0.40
     cruising
    0.40
     downlink
    0.40
    спомина
    0.40
    POSITIVE LOGITS
    англ
    0.57
     Though
    0.52
     The
    0.52
     This
    0.51
     Name
    0.49
    0.48
     Bezeichnung
    0.47
     这个
    0.47
    0.46
     อ
    0.46
    Act Density 0.493%

    No Known Activations