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

    Neuronpedia

    INDEX
    Explanations

    build upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মান
    0.44
     каждое
    0.41
    йо
    0.36
    FAQs
    0.36
     ईमान
    0.36
    users
    0.35
    стые
    0.35
     каждо
    0.35
     kebanyakan
    0.35
    産の
    0.34
    POSITIVE LOGITS
     extensively
    0.85
     heavily
    0.64
     against
    0.52
     عليها
    0.52
     throughout
    0.52
     profusely
    0.50
     freely
    0.50
     sesuatu
    0.47
     within
    0.47
     loudly
    0.47
    Act Density 0.064%

    No Known Activations