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

    Neuronpedia

    INDEX
    Explanations

    list of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ettes
    0.37
    无论是
    0.37
    通过
    0.37
    oodle
    0.36
    ผ่าน
    0.36
    engen
    0.35
     sake
    0.35
     things
    0.34
     ধরে
    0.34
    estad
    0.34
    POSITIVE LOGITS
     seznam
    0.49
     locali
    0.46
     فہرست
    0.45
     destabil
    0.44
    TypeList
    0.44
     lijst
    0.44
     лока
    0.43
     succumb
    0.43
     ország
    0.42
     فهرست
    0.42
    Act Density 0.033%

    No Known Activations