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

    Neuronpedia

    INDEX
    Explanations

    there was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     existence
    1.08
     Existence
    1.07
     esiste
    0.95
     existência
    0.94
     existed
    0.92
     exists
    0.90
     exist
    0.88
     incess
    0.87
     существует
    0.87
    esistenza
    0.87
    POSITIVE LOGITS
    쾰
    0.84
     perny
    0.80
    ריה
    0.80
    carrier
    0.79
    都不是
    0.78
    都沒有
    0.78
     resolve
    0.78
    Entries
    0.77
    Carrier
    0.76
     salah
    0.76
    Act Density 0.012%

    No Known Activations