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

    Neuronpedia

    INDEX
    Explanations

    URLs and academic publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ASK
    0.39
    ENS
    0.38
    COST
    0.37
    ADDRESS
    0.37
    asinya
    0.36
    CORE
    0.35
    ITS
    0.34
    ORIA
    0.34
    ERR
    0.33
     ہزار
    0.33
    POSITIVE LOGITS
     rjf
    0.35
     wouldnt
    0.35
     लागणार
    0.35
    ﭥ
    0.35
     मोदी
    0.35
     tamil
    0.34
     tı
    0.34
     Букмекерская
    0.34
     shoved
    0.34
     আওয়ামীলীগের
    0.34
    Act Density 0.001%

    No Known Activations