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

    Neuronpedia

    INDEX
    Explanations

    giving credit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    惧
    0.42
     चिंता
    0.39
    տն
    0.36
     આગાહી
    0.36
     isotherm
    0.35
     Conform
    0.35
     কথাবার
    0.35
    簌
    0.34
     aliphatic
    0.34
     பாதிக்கிறது
    0.34
    POSITIVE LOGITS
     credit
    2.45
    credit
    2.22
     credits
    2.20
     Credit
    2.16
    Credit
    2.16
     credited
    2.14
     crédito
    2.14
     crédit
    2.09
     क्रेडिट
    2.08
     kredit
    2.02
    Act Density 0.012%

    No Known Activations