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

    Neuronpedia

    INDEX
    Explanations

    being or existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Was
    0.99
    డింది
    0.91
     አለበት
    0.82
    Does
    0.81
    was
    0.81
     Was
    0.81
     sebuah
    0.81
    Isn
    0.81
    টি
    0.80
     էր
    0.80
    POSITIVE LOGITS
     are
    3.61
     đều
    3.36
     were
    3.19
     ovat
    3.05
    都有
    3.00
     jsou
    2.96
    都
    2.91
    都可以
    2.88
    都是
    2.87
     ஆகியோர்
    2.85
    Act Density 1.019%

    No Known Activations