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

    Neuronpedia

    INDEX
    Explanations

    free HTTPS access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     introduction
    0.51
    ުޅ
    0.46
     ocean
    0.45
    lja
    0.45
     coordinated
    0.44
     bulunduğu
    0.42
     eucalyptus
    0.42
     downstairs
    0.41
     Thames
    0.41
     canned
    0.41
    POSITIVE LOGITS
     ترین
    0.65
     بە
    0.58
    。
    0.53
    㩴
    0.52
    toprule
    0.49
     γ
    0.49
     ক্রম
    0.49
    。\
    0.49
     Litecoin
    0.49
     मुक्त
    0.48
    Act Density 0.001%

    No Known Activations