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

    Neuronpedia

    INDEX
    Explanations

    locations and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thee
    1.32
     pikir
    1.27
     Из
    1.24
     fijn
    1.22
     terus
    1.19
     épaisse
    1.18
     longue
    1.15
     eerst
    1.15
     solucionar
    1.12
     ovog
    1.11
    POSITIVE LOGITS
    ні
    1.41
     elicited
    1.23
    মুখী
    1.15
     தேர்தல்
    1.14
    好奇
    1.14
    ἱ
    1.13
     フェ
    1.12
    时间
    1.11
    事务
    1.11
    nf
    1.10
    Act Density 0.168%

    No Known Activations