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

    Neuronpedia

    INDEX
    Explanations

    setting the stage for discourse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ceremonial
    0.58
     gunfire
    0.58
     virulent
    0.55
     tir
    0.52
     coinc
    0.51
     vehement
    0.50
     coincidence
    0.50
     aniversario
    0.50
     lucro
    0.50
     utilitarian
    0.50
    POSITIVE LOGITS
     এবং
    0.91
    そして
    0.86
     आणि
    0.84
    और
    0.84
    and
    0.82
     અને
    0.82
     ਅਤੇ
    0.81
     and
    0.81
     ಮತ್ತು
    0.81
    และ
    0.80
    Act Density 0.001%

    No Known Activations