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

    Neuronpedia

    INDEX
    Explanations

    seeing this or navigating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tecnologie
    0.45
    اس
    0.44
    گ
    0.42
     konz
    0.42
    殚
    0.42
    وجه
    0.42
    س
    0.41
     ඉද
    0.41
     éc
    0.41
     fourn
    0.41
    POSITIVE LOGITS
     cookies
    0.48
     gstlal
    0.43
    ffffff
    0.42
    Bacteria
    0.42
     schizophrenia
    0.42
    😒
    0.42
     aday
    0.41
    <unused27>
    0.41
     pengendalian
    0.40
     $(-
    0.40
    Act Density 0.005%

    No Known Activations