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

    Neuronpedia

    INDEX
    Explanations

    place of refuge or special interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.58
     rn
    0.58
     grandes
    0.54
     italiano
    0.53
     Г
    0.51
     হেলিকপ্ট
    0.51
     idi
    0.50
     printemps
    0.50
     desliz
    0.50
     кури
    0.50
    POSITIVE LOGITS
    f
    0.96
    ве
    0.71
    ла
    0.68
    ,
    0.64
    да
    0.57
    त्र
    0.57
    ↵
    0.57
    ба
    0.57
    ००
    0.57
    c
    0.57
    Act Density 0.001%

    No Known Activations