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

    Neuronpedia

    INDEX
    Explanations

    cybersecurity, life extension, programming libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    去的
    0.41
     marav
    0.40
     हल्
    0.39
    制的
    0.39
     गेला
    0.38
     シュ
    0.38
     प्रकर
    0.37
     PARA
    0.37
    くい
    0.37
    斥
    0.37
    POSITIVE LOGITS
     niem
    0.44
    svet
    0.41
    茗
    0.39
    宝宝
    0.37
     endors
    0.37
     %#
    0.35
     বাড়
    0.35
    weiten
    0.35
    sweater
    0.35
     দেওয়া
    0.34
    Act Density 0.000%

    No Known Activations