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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standing
    0.80
     Standing
    0.73
    Standing
    0.69
    standing
    0.64
     стоя
    0.62
    excited
    0.56
     excited
    0.56
     traveling
    0.55
     travelling
    0.52
    Traveling
    0.51
    POSITIVE LOGITS
     hems
    0.40
    ಕ್ಕೆ
    0.37
     merken
    0.37
     несо
    0.37
    Мен
    0.35
     rolled
    0.35
    ophen
    0.34
     пари
    0.34
     ঘোষিত
    0.34
     لئے
    0.33
    Act Density 0.013%

    No Known Activations