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

    Neuronpedia

    INDEX
    Explanations

    this self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rigs
    0.44
     descobrir
    0.39
     rig
    0.38
     brews
    0.38
     irons
    0.37
    Volumes
    0.37
     brewers
    0.36
     alc
    0.35
     कसे
    0.35
     Phát
    0.35
    POSITIVE LOGITS
     this
    0.63
     هذا
    0.60
    this
    0.59
     denna
    0.59
     този
    0.56
     இந்த
    0.53
     این
    0.52
     denne
    0.51
    นี้
    0.50
     この
    0.50
    Act Density 0.004%

    No Known Activations