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

    Neuronpedia

    INDEX
    Explanations

    social interaction and AI understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וא
    0.42
     estimates
    0.36
     narrows
    0.36
     contributors
    0.36
     spender
    0.34
     unlocks
    0.34
     thighs
    0.34
     allows
    0.34
     הנו
    0.34
     warranty
    0.34
    POSITIVE LOGITS
    ərd
    0.38
    ündung
    0.38
    util
    0.37
     tentang
    0.37
    lardı
    0.37
    𝐫
    0.37
    áln
    0.35
    getValue
    0.35
    lí
    0.35
    𝐭
    0.35
    Act Density 3.365%

    No Known Activations