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

    Neuronpedia

    INDEX
    Explanations

    numbers and text after zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಳು
    0.40
    绿
    0.38
    ряду
    0.38
     trig
    0.37
     آز
    0.37
     ostr
    0.37
     plato
    0.37
     terr
    0.37
    opl
    0.37
     spender
    0.36
    POSITIVE LOGITS
     드리
    0.40
     Hybrid
    0.36
     propos
    0.35
    穸
    0.35
    rative
    0.35
     ದಾಖ
    0.35
    ICOS
    0.35
    풉
    0.35
    Hybrid
    0.34
     MFP
    0.34
    Act Density 0.002%

    No Known Activations