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

    Neuronpedia

    INDEX
    Explanations

    yo, dejo, voici, лось

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    1.33
    م
    1.27
    க
    1.26
    นิด
    1.23
    க்
    1.21
    ために
    1.21
    ため
    1.18
    k
    1.11
    equalsIgnoreCase
    1.11
    en
    1.09
    POSITIVE LOGITS
    Ŷ
    1.13
    šnje
    1.04
    ية
    0.97
     fraught
    0.97
    臾
    0.96
    forest
    0.95
     কল্প
    0.94
     implantation
    0.94
     પરિ
    0.94
    še
    0.93
    Act Density 0.043%

    No Known Activations