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

    Neuronpedia

    INDEX
    Explanations

    long contract terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interchanges
    0.46
     checklists
    0.42
     regulations
    0.38
     corresponded
    0.37
     hab
    0.37
     विनियम
    0.37
    mediawiki
    0.37
     வா
    0.36
     enact
    0.36
    隋
    0.36
    POSITIVE LOGITS
     multi
    0.84
     langfrist
    0.83
     multimillion
    0.73
    長期
    0.69
     longterm
    0.68
    multi
    0.67
    ยาว
    0.64
     طويلة
    0.64
    三年
    0.63
     uzun
    0.63
    Act Density 0.005%

    No Known Activations