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

    Neuronpedia

    INDEX
    Explanations

    malaysia following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    総
    0.44
     Duf
    0.39
     Spell
    0.38
    dü
    0.38
    PD
    0.37
     trif
    0.37
     Government
    0.36
     concord
    0.36
     dü
    0.35
     পশ্চ
    0.34
    POSITIVE LOGITS
     Astro
    0.73
     astro
    0.72
    astro
    0.58
     Malays
    0.55
     Malay
    0.51
    Malaysia
    0.51
     malay
    0.50
    Malay
    0.49
     astrocytes
    0.49
     Malaysia
    0.48
    Act Density 0.001%

    No Known Activations