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

    Neuronpedia

    INDEX
    Explanations

    technical jargon

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    机会
    0.57
    এস
    0.54
    턴
    0.52
     રૂપ
    0.51
    イズ
    0.50
    MainActivity
    0.50
    既存
    0.50
    teo
    0.48
    瑁
    0.48
     printr
    0.47
    POSITIVE LOGITS
     sardines
    0.65
     embaixo
    0.64
     rw
    0.60
     nele
    0.58
     boca
    0.56
     equilibria
    0.55
     conformity
    0.55
    obu
    0.55
    isHidden
    0.55
     correspond
    0.54
    Act Density 0.001%

    No Known Activations