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

    Neuronpedia

    INDEX
    Explanations

    pursue their own interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marketable
    0.55
     Dahmer
    0.45
     ruthless
    0.44
     buy
    0.43
    oksatta
    0.43
     submersible
    0.43
    子は
    0.43
     yachts
    0.43
     ribbed
    0.42
    ėti
    0.42
    POSITIVE LOGITS
    نا
    0.60
    ल
    0.58
    ن
    0.57
    ك
    0.57
    ل
    0.56
    ا
    0.51
    Aprend
    0.50
    يديو
    0.49
    Eine
    0.49
    ناد
    0.48
    Act Density 0.002%

    No Known Activations