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

    Neuronpedia

    INDEX
    Explanations

    anyone else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उबाल
    0.45
    rels
    0.44
    銛
    0.43
    imente
    0.43
    料理
    0.42
    ר
    0.42
    versive
    0.41
     कप्तान
    0.41
    ussels
    0.41
    藻
    0.41
    POSITIVE LOGITS
     Werte
    0.57
     અવ
    0.49
     നേര
    0.46
    笉
    0.45
     ተግባ
    0.45
     authorizing
    0.45
     percent
    0.43
     كانت
    0.42
     grieve
    0.42
     tarefas
    0.42
    Act Density 0.006%

    No Known Activations