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

    Neuronpedia

    INDEX
    Explanations

    language and interpreting subjective experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PDE
    0.51
     একা
    0.50
    '&
    0.50
     FHWA
    0.49
    PHIA
    0.48
     אר
    0.47
    {&
    0.47
     каких
    0.47
     repeats
    0.47
    '?
    0.47
    POSITIVE LOGITS
    й
    0.48
    يزة
    0.46
    語
    0.46
    лому
    0.45
     Morning
    0.44
    ра
    0.43
     ami
    0.43
    v
    0.43
     ngữ
    0.42
     morning
    0.41
    Act Density 0.003%

    No Known Activations