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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.80
     \\
    0.76
     वर्ण
    0.72
    ,-\
    0.67
     sposób
    0.67
     gew
    0.66
    计
    0.65
    泹
    0.65
     ખ
    0.65
     vlast
    0.64
    POSITIVE LOGITS
    ameni
    0.65
    ervo
    0.65
     hemodynamic
    0.64
     publicar
    0.64
    polo
    0.63
     ハート
    0.63
    сер
    0.63
    weekly
    0.62
     throughout
    0.62
    availability
    0.62
    Act Density 0.010%

    No Known Activations