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

    Neuronpedia

    INDEX
    Explanations

    leverages/cater/using + preposition/noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     almonds
    0.69
     ಅದನ್ನು
    0.68
     cucumbers
    0.66
     адам
    0.64
     землю
    0.63
     crustaceans
    0.61
    它
    0.61
    🌜
    0.61
     edibles
    0.61
     ljudi
    0.60
    POSITIVE LOGITS
    ود
    0.55
     پنج
    0.54
    ുള്ള
    0.51
     уважаемые
    0.51
    ղ
    0.50
     جول
    0.50
    사의
    0.49
    ức
    0.49
     යන
    0.48
    ています
    0.48
    Act Density 0.625%

    No Known Activations