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

    Neuronpedia

    INDEX
    Explanations

    target audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఒ
    0.36
    ագ
    0.35
     jednotliv
    0.34
    ગ્ર
    0.33
    сіб
    0.33
    ័រ
    0.33
    மனித
    0.32
    ইতে
    0.32
     বৎসর
    0.32
    ophosph
    0.31
    POSITIVE LOGITS
     audience
    2.84
     audiences
    2.53
    audience
    2.52
     Audience
    2.42
     audiencia
    2.05
    观众
    1.88
     ауди
    1.88
    觀眾
    1.80
     target
    1.68
     दर्शकों
    1.66
    Act Density 0.205%

    No Known Activations