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

    Neuronpedia

    INDEX
    Explanations

    choosing what to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endogenous
    0.37
     prothorace
    0.29
     dint
    0.28
     Bcl
    0.27
     degeneracy
    0.27
     invariant
    0.27
     antisense
    0.27
     GoObject
    0.27
     liderazgo
    0.27
     jihad
    0.26
    POSITIVE LOGITS
     เลือก
    0.38
     원하는
    0.37
     выбрать
    0.36
     ഉപകരണ
    0.34
     uży
    0.31
     wybrać
    0.31
    ël
    0.31
    လိုအပ်
    0.31
    🛒
    0.30
    świet
    0.30
    Act Density 0.000%

    No Known Activations