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

    Neuronpedia

    INDEX
    Explanations

    cryptocurrency copyright inflation shorts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لیم
    0.42
     reconstru
    0.42
     mucosa
    0.40
    …………..
    0.40
     Kiya
    0.40
     носи
    0.40
    GALAD
    0.39
     TRIP
    0.39
     LIM
    0.39
     administr
    0.39
    POSITIVE LOGITS
    remember
    0.46
    i
    0.38
    axios
    0.38
    fur
    0.37
    t
    0.36
     remember
    0.36
    Í
    0.36
    ])){
    0.36
    define
    0.35
    /.
    0.35
    Act Density 0.000%

    No Known Activations